© 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. 73725
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    oxane
    -0.60
     wireType
    -0.56
     forza
    -0.50
    Ծանոթ
    -0.50
     Assn
    -0.49
     épaules
    -0.49
    getHeader
    -0.49
     Reinh
    -0.49
    fda
    -0.48
    ffine
    -0.48
    POSITIVE LOGITS
     noqa
    0.57
    Novel
    0.51
     defaultstate
    0.49
     Opus
    0.47
    Opus
    0.46
    stanza
    0.45
    opus
    0.45
    anthem
    0.45
    poem
    0.45
    enumi
    0.45
    Activations Density 0.001%

    No Known Activations