© 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. 96642
    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
     that
    -0.57
     Machado
    -0.50
     issued
    -0.50
     That
    -0.49
     ‘
    -0.49
     occurred
    -0.48
     fitted
    -0.48
     did
    -0.47
     performed
    -0.47
     happened
    -0.47
    POSITIVE LOGITS
    IndentedString
    0.78
    ppure
    0.71
    Geplaatst
    0.67
    tagext
    0.62
     brancas
    0.58
    Pyx
    0.57
     étoit
    0.56
    setVerticalGroup
    0.55
    bbene
    0.53
     varandra
    0.52
    Activations Density 0.019%

    No Known Activations