© 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. 4453
    Prev
    Next
    INDEX
    Explanations

    read

    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
    AndEndTag
    -0.77
     تضيفلها
    -0.76
     initComponents
    -0.69
    PreferredItem
    -0.69
    RectangleBorder
    -0.67
    tvguidetime
    -0.66
    InjectAttribute
    -0.66
    клопе
    -0.65
     }{@
    -0.63
    PerformLayout
    -0.63
    POSITIVE LOGITS
     Shreve
    0.56
    فق
    0.52
     oublié
    0.51
    moga
    0.51
     Speak
    0.50
    شك
    0.50
     μή
    0.49
     survey
    0.49
     Resist
    0.46
     epit
    0.46
    Activations Density 0.002%

    No Known Activations