© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1115
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    root
    -0.46
    цездатний
    -0.44
     himself
    -0.43
     useCallback
    -0.42
     بيها
    -0.42
    ]--;
    -0.41
    :_
    -0.40
    kson
    -0.40
     root
    -0.40
    ="../
    -0.40
    POSITIVE LOGITS
    DllImport
    0.64
    ISupport
    0.63
    MessageOf
    0.61
    DockStyle
    0.61
    ColumnHeaders
    0.58
    onomía
    0.56
    IContainer
    0.56
    ército
    0.56
    resz
    0.54
    ImageContext
    0.54
    Activations Density 0.009%

    No Known Activations