Model age rating
gemma-2-2b-it-abliterated
Not assessedSafety-mod — Safety-modification (abliteration / manual censoring) — may be a legitimate change
- Safety refusals removed (abliteration)
Integrity — a safety-modification. Safety-modification (abliteration / manual censoring) — may be a legitimate change. A safety-modification — abliteration, or a manual censoring change — may be a legitimate modification (for example, removing over-refusal for research). The register distinguishes it from a covert injection precisely because this class carries a higher false-positive risk. It is rated 18+ because the safety behaviour was witnessed to have changed, not because the change is presumed malicious.
Think this rating is wrong? A rating is a witnessed finding, corrected on evidence — especially a safety-modification finding, which can be a legitimate change. If you believe this rating is wrong, or you are the uploader and wish to respond, email legend@vulcora.se. We never certify a model safe.
What the uploader's card said
The card does not address a safety change.
What Protora observed
Safety refusals removed, witnessed — the model no longer refuses the harmful battery its official reference declines.
- Base model
- google/gemma-2-2b-it · google
- Parameters
- 2B
- Family
- Gemma-2
- Licence
- gemma
- Downloads (HuggingFace)
- 71k all-time · 50k in the last 30 days · 52 likes · sampled 2026-07-14
- Assessed
- 2026-07 (Protora Phase-0 coverage)
What this rating means. A rating of 18+ records that adult or harmful content was observed in the model, with evidence. It is an advisory, not a warranty. A “not rated” result means nothing was witnessed on our coverage — it is not a certification that a model is safe for children.
View the model on HuggingFace ↗
Read the full witnessed finding on Protora's record ↗
The finding and the card quote are presented as Protora publishes them, from protora.vulcora.se. Adult content itself is never shown; harmful outputs are withheld. See how we rate.