© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 1309
    Prev
    Next
    INDEX
    Explanations

    references to safety or safety-related information

    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
    Negative Logits
    thouse
    -0.62
    InitVars
    -0.61
     resourceCulture
    -0.57
     denial
    -0.55
    Izvori
    -0.53
    Източници
    -0.52
    encodeWith
    -0.52
    fou
    -0.51
    gameserver
    -0.51
    dfunding
    -0.51
    POSITIVE LOGITS
     safe
    4.31
    safe
    4.03
     safety
    3.97
     Safe
    3.88
    Safe
    3.83
     Safety
    3.69
    safety
    3.67
    Safety
    3.63
     safely
    3.61
     safer
    3.61
    Activations Density 0.139%

    No Known Activations