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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13214
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.63
    kuuta
    -0.60
     للاسماء
    -0.57
    utnik
    -0.57
    %)$
    -0.56
    /−
    -0.56
    OCCURRED
    -0.55
    ]--;
    -0.55
     виправивши
    -0.55
    ")));
    -0.55
    POSITIVE LOGITS
    ViewImports
    0.56
    Население
    0.54
    锈钢
    0.48
    ,
    0.46
     geldig
    0.45
     كومونز
    0.45
     mergeFrom
    0.45
    Наводи
    0.44
    ąb
    0.44
    ագրություններ
    0.43
    Activations Density 0.019%

    No Known Activations