© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11884
    Prev
    Next
    INDEX
    Explanations

    descriptions

    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
    ün
    -0.80
    帖最后由
    -0.76
     typelib
    -0.70
    oush
    -0.69
     AssemblyProduct
    -0.66
     ornate
    -0.66
     AspNetCore
    -0.64
    AntiForgeryToken
    -0.61
    uminum
    -0.59
    utilisons
    -0.59
    POSITIVE LOGITS
    UrlResolution
    0.53
    AlterField
    0.53
    sz
    0.52
    RegressionTest
    0.50
    
    0.49
     vivos
    0.47
    pement
    0.47
     cebola
    0.47
    kurat
    0.47
    shop
    0.45
    Activations Density 0.016%

    No Known Activations