Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 369
    Prev
    Next
    INDEX
    Explanations

    weaken

    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
    MigrationBuilder
    -0.90
    s
    -0.88
     ExecuteAsync
    -0.87
    libft
    -0.78
    Wea
    -0.70
    ene
    -0.69
    ship
    -0.62
     betweenstory
    -0.61
     Roskov
    -0.61
    TypedDataSet
    -0.60
    POSITIVE LOGITS
     WebDriverWait
    0.57
    idom
    0.53
    mahami
    0.47
     everything
    0.46
     réessayer
    0.46
    linik
    0.46
    underland
    0.46
    timeouts
    0.46
    ondy
    0.45
    orologio
    0.44
    Activations Density 0.030%

    No Known Activations