© 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. 12476
    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
     strokes
    -0.72
     stroke
    -0.65
     Strokes
    -0.65
    STROKE
    -0.65
     CreateTagHelper
    -0.64
    stroke
    -0.62
     Stroke
    -0.59
    Stroke
    -0.59
    makeConstraints
    -0.58
    strokes
    -0.56
    POSITIVE LOGITS
     يتيمه
    0.74
    elfare
    0.63
     rhestr
    0.62
     fubject
    0.60
    PageContext
    0.59
    ^(@)
    0.59
     transfieras
    0.59
     Voiture
    0.58
     Мексичка
    0.58
     ſche
    0.57
    Activations Density 0.037%

    No Known Activations