© 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
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2813
    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
    ,
    -1.20
    .
    -0.65
    :
    -0.53
    /
    -0.40
     future
    -0.39
    -
    -0.39
     "
    -0.35
     real
    -0.34
    ;
    -0.34
     U
    -0.33
    POSITIVE LOGITS
     Efq
    1.00
     autorytatywna
    0.94
     Reſ
    0.91
    ValueStyle
    0.90
     whoſe
    0.89
     Majefty
    0.88
    parsedMessage
    0.88
     myſelf
    0.88
     Theſe
    0.86
     itſelf
    0.85
    Activations Density 0.173%

    No Known Activations