© 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. 73622
    Prev
    Next
    INDEX
    Explanations

    Computer code

    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
    disposing
    -0.53
     CEL
    -0.48
    berge
    -0.47
    fromnode
    -0.47
    CEN
    -0.46
    reciated
    -0.46
    Ellips
    -0.44
    MouseAdapter
    -0.44
    Bos
    -0.43
     CEN
    -0.43
    POSITIVE LOGITS
    parsedMessage
    0.59
    UserScript
    0.57
     Lordships
    0.53
     للتو
    0.50
    帖最后由
    0.50
    TagMode
    0.49
    าสตร์
    0.49
    pts
    0.48
    ({
    0.48
    ChildScrollView
    0.48
    Activations Density 0.000%

    No Known Activations