© 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. 5-CLT-HP
    7. 776
    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
     "..\..\
    -0.66
     transférez
    -0.58
     Slavery
    -0.57
    Jeografia
    -0.57
     Duplicate
    -0.57
     Dedicated
    -0.57
     jsPsych
    -0.57
     Squeeze
    -0.56
     numerus
    -0.56
     cherchés
    -0.56
    POSITIVE LOGITS
    ExtendWith
    0.52
    DoubleQuotes
    0.50
    XmlAccessType
    0.48
    FunctionFlags
    0.47
    FromNib
    0.44
     مشين
    0.43
    msgTypes
    0.43
    __(/*!
    0.41
    reportWebVitals
    0.41
    ViewImports
    0.39
    Activations Density 0.000%

    No Known Activations