© 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. 4-CLT-HP
    7. 3540
    Prev
    Next
    INDEX
    Explanations

    code and URLs

    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
    principalColumn
    -0.86
     ModelExpression
    -0.85
     مشين
    -0.79
    parsedMessage
    -0.78
     purpoſe
    -0.77
    ThroughAttribute
    -0.76
    قایناق‌لار
    -0.76
    पया
    -0.73
     Majefty
    -0.73
    exitRule
    -0.73
    POSITIVE LOGITS
     re
    0.49
     primas
    0.49
    ors
    0.44
    cts
    0.44
    cta
    0.42
    ERAL
    0.41
    s
    0.40
     s
    0.38
    cerrar
    0.37
    S
    0.37
    Activations Density 0.016%

    No Known Activations