© 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. 4-CLT-HP
    7. 4389
    Prev
    Next
    INDEX
    Explanations

    simulation

    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
    heem
    -0.52
     erythrocytes
    -0.51
    دانشنامهٔ
    -0.48
    SizeF
    -0.48
     Закон
    -0.48
    entiel
    -0.47
    rlpool
    -0.47
    HtmlAttribute
    -0.47
    adpleegd
    -0.46
    )_/¯
    -0.45
    POSITIVE LOGITS
    ValueStyle
    0.73
     Савезне
    0.62
     '\\;'
    0.57
    ANTLR
    0.55
     виправивши
    0.54
     laboratory
    0.54
     training
    0.53
    XtraGrid
    0.53
     software
    0.52
    GeoNames
    0.52
    Activations Density 0.008%

    No Known Activations