© 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. 20-CLT-HP
    7. 75534
    Prev
    Next
    INDEX
    Explanations

    Code, news, legal documents

    np_max-act-logits · 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
     للمعارف
    -0.82
    windowFixed
    -0.81
    awtextra
    -0.77
    AddTagHelper
    -0.75
    LookAnd
    -0.73
     AssemblyCulture
    -0.70
     Roskov
    -0.69
    клопе
    -0.69
    ziplin
    -0.69
    ValueStyle
    -0.68
    POSITIVE LOGITS
     Bre
    0.36
    breast
    0.36
     esqu
    0.36
    忙
    0.34
     beri
    0.34
    
    0.34
    χεία
    0.32
    bux
    0.32
    ều
    0.31
    assisted
    0.30
    Activations Density 0.000%

    No Known Activations