© 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. 1259
    Prev
    Next
    INDEX
    Explanations

    ctile

    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
    chenkt
    -0.50
    adal
    -0.50
     vs
    -0.45
    合物
    -0.43
     sau
    -0.42
    jsxFileName
    -0.42
    աս
    -0.42
    messung
    -0.42
    meability
    -0.42
     sino
    -0.41
    POSITIVE LOGITS
    StoryboardSegue
    0.96
     Мексичка
    0.79
     poffe
    0.79
     fubject
    0.78
    ſelf
    0.77
    WithMany
    0.73
    migrationBuilder
    0.72
    ."],
    0.72
     purpoſe
    0.71
     Efq
    0.70
    Activations Density 0.080%

    No Known Activations