© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8984
    Prev
    Next
    INDEX
    Explanations

    function

    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
     function
    -0.62
     functions
    -0.48
     esquecer
    -0.47
     Functions
    -0.47
     Function
    -0.46
    嘩
    -0.45
    function
    -0.45
    Functions
    -0.45
     函数
    -0.44
    Function
    -0.43
    POSITIVE LOGITS
    RectangleBorder
    0.79
     متعلقه
    0.77
     بيها
    0.72
    mybatisplus
    0.68
    UnsafeEnabled
    0.67
    ⓧ
    0.67
    ValueStyle
    0.66
    IsContent
    0.65
     المعيارى
    0.64
    enumii
    0.63
    Activations Density 0.015%

    No Known Activations