© 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. 40612
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    seguida
    -0.57
     VizieR
    -0.54
    čnega
    -0.52
    ként
    -0.48
     sidan
    -0.48
     canto
    -0.47
    گانه
    -0.47
    komna
    -0.47
    NamedQueries
    -0.46
     avulla
    -0.46
    POSITIVE LOGITS
     متعلقه
    0.79
    بوابة
    0.70
     الرياضيه
    0.62
    存于互联网档案馆
    0.61
    ographia
    0.61
    ViewImports
    0.60
    CppMethod
    0.60
     للاسماء
    0.60
     Ceramby
    0.59
     Drog
    0.59
    Activations Density 1.818%

    No Known Activations