© 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. 20-CLT-HP
    7. 74731
    Prev
    Next
    INDEX
    Explanations

    as

    np_max-act-logits · 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
     autorytatywna
    -0.91
     Roskov
    -0.85
     estekak
    -0.85
     doInBackground
    -0.84
    BeginInit
    -0.84
    istoitu
    -0.81
    WebElementEntity
    -0.78
    Jeografia
    -0.77
    TagMode
    -0.77
    ConstraintMaker
    -0.77
    POSITIVE LOGITS
     reference
    0.93
     check
    0.79
     control
    0.69
     references
    0.65
     training
    0.59
     refer
    0.56
     yards
    0.55
    reference
    0.54
    check
    0.54
     comparison
    0.54
    Activations Density 0.003%

    No Known Activations