© 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. 12199
    Prev
    Next
    INDEX
    Explanations

    code and migration

    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
    Lähteet
    -0.65
    Autoritní
    -0.63
    SharedCtor
    -0.60
    windowFixed
    -0.57
    PreferredItem
    -0.53
    ValueStyle
    -0.52
    TestingModule
    -0.52
     للمعارف
    -0.52
     migrating
    -0.48
    ьаж
    -0.48
    POSITIVE LOGITS
    addPreferredGap
    0.54
     Diener
    0.51
     estekak
    0.48
    brio
    0.48
    Geplaatst
    0.47
    катерина
    0.46
    (!__
    0.43
    ersonic
    0.42
    efits
    0.42
     Railroad
    0.42
    Activations Density 0.011%

    No Known Activations