© 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. 43864
    Prev
    Next
    INDEX
    Explanations

    locations

    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
    istoitu
    -0.69
     فريبيس
    -0.69
    ыгана
    -0.67
    ⓧ
    -0.66
    aphone
    -0.66
     متعلقه
    -0.65
     EconPapers
    -0.64
     citoy
    -0.63
     الاطلاع
    -0.62
    Дереккөздер
    -0.62
    POSITIVE LOGITS
    <bos>
    0.65
     Pvt
    0.49
     Crimean
    0.47
     Telangana
    0.46
     Comprometido
    0.46
    {
    0.46
    icidio
    0.46
     Madras
    0.45
     scand
    0.44
     Protestantism
    0.44
    Activations Density 0.091%

    No Known Activations