Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1915
    Prev
    Next
    INDEX
    Explanations

    document excerpts

    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
    存于互联网档案馆
    -0.73
    ↵
    -0.72
     ***!
    -0.68
    SPJ
    -0.65
     للمعارف
    -0.64
    ]");
    -0.60
    例文帳に追加
    -0.59
    ())))
    -0.59
    `);
    -0.57
    ")));
    -0.57
    POSITIVE LOGITS
     of
    0.81
     more
    0.72
     simply
    0.69
     just
    0.68
     now
    0.63
    ,
    0.59
     authorised
    0.58
     basically
    0.56
     that
    0.56
     most
    0.56
    Activations Density 0.001%

    No Known Activations