© 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. 5-CLT-HP
    7. 6183
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Negative Logits
     betweenstory
    -1.10
    InvalidProtocol
    -0.86
     cherchés
    -0.86
    GOTREF
    -0.76
     jsPsych
    -0.75
    :✨
    -0.73
    DoubleQuotes
    -0.73
     }</
    -0.72
    memoized
    -0.72
    RegressionTest
    -0.69
    POSITIVE LOGITS
    EDEFAULT
    0.42
     heart
    0.41
     Lower
    0.39
    getDrawable
    0.38
     then
    0.36
    ftagPool
    0.36
    ereza
    0.36
    
    0.36
    cupertino
    0.36
     lower
    0.36
    Activations Density 0.003%

    No Known Activations