© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1075
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    <bos>
    -0.82
    contentLoaded
    -0.58
    jspb
    -0.48
    bitField
    -0.48
     coming
    -0.48
    ubwa
    -0.47
     viendo
    -0.47
    攻
    -0.46
    Coming
    -0.44
    另
    -0.44
    POSITIVE LOGITS
     autorytatywna
    0.82
     فريبيس
    0.80
     виправивши
    0.69
    ArgsConstructor
    0.68
    twimg
    0.63
     مشين
    0.59
     ujednoznacz
    0.59
     समीक्षक
    0.57
     initComponents
    0.57
    orianCalendar
    0.57
    Activations Density 0.007%

    No Known Activations