© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42196
    Prev
    Next
    INDEX
    Explanations

    style

    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
     style
    -1.03
     Style
    -0.99
     itſelf
    -0.98
    style
    -0.98
     purpoſe
    -0.96
     STYLE
    -0.94
     raiſ
    -0.92
    Style
    -0.91
     스타일
    -0.87
    ſelf
    -0.84
    POSITIVE LOGITS
    .
    0.57
    I
    0.52
    n
    0.52
     أعلام
    0.49
    s
    0.48
    م
    0.47
    ...
    0.46
     
    0.46
    Continue
    0.46
     into
    0.45
    Activations Density 0.055%

    No Known Activations