© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1027
    Prev
    Next
    INDEX
    Explanations

    by

    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
     vies
    -0.42
     tied
    -0.41
    Aiheesta
    -0.40
     showing
    -0.40
    ⓧ
    -0.40
     parts
    -0.39
    views
    -0.39
     views
    -0.39
     improved
    -0.39
    ś
    -0.38
    POSITIVE LOGITS
     ویکی‌پدیا
    0.93
     Normdatei
    0.90
    Rujuakan
    0.83
     propOrder
    0.81
     فريبيس
    0.80
     defaultstate
    0.79
    évaluateur
    0.79
    webElementXpaths
    0.78
     InputDecoration
    0.75
    uxxxx
    0.73
    Activations Density 0.020%

    No Known Activations