© 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. 0-CLT-HP
    7. 95292
    Prev
    Next
    INDEX
    Explanations

    time/change

    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
     blessés
    -0.57
     blessé
    -0.50
    analisi
    -0.50
    <bos>
    -0.46
     chargés
    -0.43
     aveug
    -0.42
    NSY
    -0.40
     ulang
    -0.40
    hyo
    -0.40
     Biôgrafia
    -0.40
    POSITIVE LOGITS
     ExecuteAsync
    0.75
    
    0.67
    CloseOperation
    0.63
    httphttps
    0.63
     nakalista
    0.63
    tagHelperRunner
    0.62
    IsMutable
    0.62
     Dostupné
    0.60
    脚注の使い方
    0.60
     initComponents
    0.59
    Activations Density 0.050%

    No Known Activations