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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 39937
    Prev
    Next
    INDEX
    Explanations

    ile

    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
     StatefulWidget
    -0.65
     ile
    -0.62
    dart
    -0.51
     GenerationType
    -0.49
    ்கு
    -0.48
    skab
    -0.47
    पया
    -0.47
    ту
    -0.45
    ouge
    -0.45
    风的
    -0.45
    POSITIVE LOGITS
    queryInterface
    0.63
    Արտաքին
    0.59
    Архівовано
    0.57
     onOptions
    0.56
    oprot
    0.55
     Kitz
    0.55
    hombo
    0.54
    DBNull
    0.54
     Audiodateien
    0.54
    basicConfig
    0.54
    Activations Density 1.668%

    No Known Activations