© 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. 0-CLT-HP
    7. 44193
    Prev
    Next
    INDEX
    Explanations

    Code and copyright notices

    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
     bough
    -1.37
    ल्प
    -0.51
    ുള്ള
    -0.50
     Do
    -0.49
    REF
    -0.49
    ঙ্গ
    -0.48
     any
    -0.47
     hace
    -0.47
    user
    -0.46
    unks
    -0.46
    POSITIVE LOGITS
    writeField
    0.91
    parsedMessage
    0.81
    mergeFrom
    0.77
    queryInterface
    0.77
    LookAnd
    0.71
     ModelExpression
    0.70
    makeConstraints
    0.69
    CloseOperation
    0.68
    Portail
    0.65
    Externí
    0.63
    Activations Density 0.561%

    No Known Activations