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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 94656
    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
    ↵
    -0.52
     This
    -0.42
    <bos>
    -0.42
    ↵↵
    -0.42
    ...
    -0.41
     In
    -0.40
     like
    -0.39
     StringVar
    -0.39
     misschien
    -0.39
    \
    -0.37
    POSITIVE LOGITS
    AccessorTable
    0.82
    oredCriteria
    0.79
     مشين
    0.79
    ########.
    0.77
     kasarigan
    0.76
    WithIOException
    0.76
    expandindo
    0.75
     ویکی‌پدی
    0.74
    )");
    
    0.74
    soort
    0.73
    Activations Density 0.003%

    No Known Activations