© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 6561
    Prev
    Next
    INDEX
    Explanations

    mentions of safety or the concept of safety

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     safe
    -0.93
    safe
    -0.82
     Safe
    -0.82
    Safe
    -0.74
     SAFE
    -0.70
    Healthy
    -0.66
    fastjson
    -0.63
     Healthy
    -0.60
     secure
    -0.59
    healthy
    -0.59
    POSITIVE LOGITS
     safety
    2.53
     Safety
    2.41
    Safety
    2.33
    safety
    2.30
     SAFETY
    2.16
    SAFETY
    1.91
    afety
    1.57
     sécurité
    1.40
     veiligheid
    1.30
     seguridad
    1.27
    Activations Density 0.005%

    No Known Activations