© 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. 640
    Prev
    Next
    INDEX
    Explanations

    scientific/technical writing

    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
    <bos>
    -0.88
     betweenstory
    -0.83
    новниш
    -0.77
    Дереккөздер
    -0.71
    tvguidetime
    -0.71
    Tikang
    -0.70
    RegressionTest
    -0.70
     ligiloj
    -0.70
    出版年
    -0.69
    TypedDataSet
    -0.68
    POSITIVE LOGITS
    glGen
    0.46
    .\\
    0.43
    TagHelpers
    0.43
     igång
    0.41
     ≥
    0.41
     spéciale
    0.40
    InputLabel
    0.40
     Fatal
    0.40
    hagen
    0.39
     fiz
    0.39
    Activations Density 0.032%

    No Known Activations