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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93190
    Prev
    Next
    INDEX
    Explanations

    truncated texts

    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
    .
    -0.88
     is
    -0.79
     “
    -0.75
    -
    -0.72
     in
    -0.71
     as
    -0.70
     are
    -0.69
     -
    -0.68
    “
    -0.68
     (
    -0.64
    POSITIVE LOGITS
    __':
    1.56
     ExecuteAsync
    1.37
    __":
    1.37
    featureID
    1.36
     ویکی‌آمباردا
    1.33
    Personensuche
    1.31
    脚注の使い方
    1.29
     EconPapers
    1.29
    Tikang
    1.28
    NUMX
    1.27
    Activations Density 0.055%

    No Known Activations