© 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. 4-CLT-HP
    7. 3285
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Autoritní
    -0.69
     '\\;'
    -0.68
    ⓧ
    -0.62
    UnusedPrivate
    -0.61
    colgroup
    -0.60
     jScrollPane
    -0.60
    tvguidetime
    -0.59
    setVerticalGroup
    -0.59
     Jacobi
    -0.58
    PCell
    -0.58
    POSITIVE LOGITS
     be
    0.62
     seguida
    0.60
     need
    0.60
     succeed
    0.54
     betra
    0.52
    be
    0.49
    need
    0.48
     have
    0.47
     bedo
    0.47
    cky
    0.46
    Activations Density 0.003%

    No Known Activations