© 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. 1-CLT-HP
    7. 13020
    Prev
    Next
    INDEX
    Explanations

    in

    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
    ↵
    -0.50
     réussi
    -0.47
     refusé
    -0.47
    ing
    -0.46
     succès
    -0.44
    ıyordu
    -0.44
    мана
    -0.43
     éxito
    -0.43
    링
    -0.43
    ımı
    -0.42
    POSITIVE LOGITS
    DockStyle
    1.09
    WithIOException
    0.99
     InputDecoration
    0.97
    WriteLiteral
    0.93
    migrationBuilder
    0.90
    principalTable
    0.85
     AssemblyCulture
    0.84
     '\\;'
    0.84
    GEBURTSDATUM
    0.83
     يتيمه
    0.82
    Activations Density 0.015%

    No Known Activations