© 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. 4572
    Prev
    Next
    INDEX
    Explanations

    but

    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
     незавершена
    -0.77
    CloseOperation
    -0.69
     autorytatywna
    -0.68
    رشف
    -0.64
    Diwedd
    -0.61
    PyExc
    -0.60
    DockStyle
    -0.59
     disponibilités
    -0.59
    ThroughAttribute
    -0.58
    MethodManager
    -0.57
    POSITIVE LOGITS
     uncommon
    0.65
     unusual
    0.61
     rare
    0.61
     requires
    0.60
     introduces
    0.60
    unusual
    0.56
    TestingModule
    0.54
    CCN
    0.54
     highly
    0.54
     involves
    0.53
    Activations Density 0.019%

    No Known Activations