© 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. 45152
    Prev
    Next
    INDEX
    Explanations

    Doc, productions

    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
     Jaw
    -0.74
    wart
    -0.59
     doc
    -0.56
     Doc
    -0.55
    Jaw
    -0.50
     smtplib
    -0.49
     Document
    -0.48
    warts
    -0.47
    sonaro
    -0.47
    thousand
    -0.46
    POSITIVE LOGITS
    uxxxx
    0.70
    LookAnd
    0.67
    AlterField
    0.63
     STAM
    0.62
    complexContent
    0.61
     Elsewhere
    0.61
    脚注の使い方
    0.60
    djangoproject
    0.60
    ByPrimaryKey
    0.59
     contextLoads
    0.59
    Activations Density 1.629%

    No Known Activations