© 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. 1-CLT-HP
    7. 10639
    Prev
    Next
    INDEX
    Explanations

    stroke

    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
     stroke
    -1.27
     strokes
    -1.09
    stroke
    -1.09
     Stroke
    -1.08
    Stroke
    -0.98
     STRO
    -0.81
    STROKE
    -0.75
     Strokes
    -0.75
    strokes
    -0.69
     disambiguazione
    -0.54
    POSITIVE LOGITS
    ukone
    0.63
     thereon
    0.63
     Efq
    0.60
    
    0.59
     yyr
    0.58
    ImageContext
    0.57
    pios
    0.57
    opardy
    0.57
    UserScript
    0.56
    omenclature
    0.55
    Activations Density 0.070%

    No Known Activations