© 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. 1-CLT-HP
    7. 45630
    Prev
    Next
    INDEX
    Explanations

    scientific/technical topics

    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
     Muck
    -0.97
     muck
    -0.68
    muck
    -0.50
    getenv
    -0.50
     opp
    -0.49
    CLOCK
    -0.47
    opp
    -0.46
    Neu
    -0.46
    numbers
    -0.46
     Tore
    -0.45
    POSITIVE LOGITS
    LookAnd
    0.68
    uxxxx
    0.65
    spesies
    0.64
     للمعارف
    0.63
     mergeFrom
    0.62
     <=",
    0.61
    :+:
    0.60
    はじめに
    0.59
    AccessorTable
    0.58
    Brainz
    0.57
    Activations Density 0.010%

    No Known Activations