© 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. 5-CLT-HP
    7. 1177
    Prev
    Next
    INDEX
    Explanations

    objectives

    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
    afficheront
    -0.70
     mostrarán
    -0.68
     InputDecoration
    -0.65
     BoxDecoration
    -0.64
    MigrationBuilder
    -0.64
    جغرافيا
    -0.63
    PMailer
    -0.60
     initComponents
    -0.58
    HasBeenSet
    -0.57
    ThroughAttribute
    -0.57
    POSITIVE LOGITS
    tagext
    0.63
    sikker
    0.52
    .~(\
    0.50
    ruptedException
    0.49
     enhancing
    0.49
     blindness
    0.48
    feof
    0.47
     narkoba
    0.47
    ViewById
    0.47
     melawan
    0.47
    Activations Density 0.002%

    No Known Activations