© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13686
    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
    ,,
    -1.22
    ,,,,
    -0.87
     ,,
    -0.85
     doigts
    -0.67
     يتيمه
    -0.63
     hjär
    -0.59
     But
    -0.52
     During
    -0.51
     geográfica
    -0.51
     termica
    -0.48
    POSITIVE LOGITS
    .
    0.75
    ."));
    0.70
    ."),
    0.68
    ArrowToggle
    0.66
     ویکی‌پدیا
    0.66
    )";
    
    0.66
    .')
    0.65
    .},
    0.63
    ."],
    0.63
    daß
    0.63
    Activations Density 0.007%

    No Known Activations