© 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. 0-CLT-HP
    7. 90680
    Prev
    Next
    INDEX
    Explanations

    technical subjects

    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
    aarrggbb
    -0.95
     StatefulWidget
    -0.88
     שוליים
    -0.85
     ModelExpression
    -0.85
     AssemblyCulture
    -0.83
    يكب
    -0.83
     חיצוניים
    -0.82
    AddTagHelper
    -0.81
    NewUrlParser
    -0.77
     كومونز
    -0.77
    POSITIVE LOGITS
    ed
    0.87
    e
    0.86
    o
    0.82
    a
    0.77
    i
    0.75
    es
    0.73
    ing
    0.67
    er
    0.64
    ه
    0.62
    ion
    0.60
    Activations Density 0.391%

    No Known Activations