© 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. 13068
    Prev
    Next
    INDEX
    Explanations

    underscore

    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
     kasarigan
    -0.93
     Wicidata
    -0.88
    (&:
    -0.84
     للمعارف
    -0.83
     autorytatywna
    -0.79
    Билгалдахарш
    -0.78
    مصادر
    -0.77
     transfieras
    -0.76
    .*")]
    -0.76
    MigrationBuilder
    -0.75
    POSITIVE LOGITS
    ever
    0.45
    B
    0.45
    com
    0.45
     to
    0.43
    re
    0.42
    ed
    0.40
    hip
    0.40
    readLine
    0.39
    fulness
    0.39
    H
    0.37
    Activations Density 0.121%

    No Known Activations