© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38921
    Prev
    Next
    INDEX
    Explanations

    way

    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
     the
    -0.76
     way
    -0.65
     to
    -0.63
    ing
    -0.62
    ’
    -0.61
     
    -0.59
    ↵
    -0.57
    /
    -0.54
    -
    -0.53
    es
    -0.52
    POSITIVE LOGITS
     surla
    1.21
     CreateTagHelper
    1.20
    AsUp
    1.11
     متعلقه
    1.05
    awtextra
    1.05
    Diwedd
    1.04
    interopRequire
    1.03
    sizeCache
    1.03
    पया
    1.03
     Signalez
    1.02
    Activations Density 0.231%

    No Known Activations