© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5652
    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
    .
    -0.56
    workbench
    -0.47
    fø
    -0.47
    javax
    -0.44
     Comprometido
    -0.44
    druk
    -0.43
     arvio
    -0.43
     külön
    -0.43
     overwhelmed
    -0.43
    springframework
    -0.43
    POSITIVE LOGITS
     nahilalakip
    0.90
    tagHelperRunner
    0.90
    ніципалі
    0.81
     but
    0.76
    SharedCtor
    0.75
     propOrder
    0.73
     <<<<<<<<<<<<<<
    0.73
    tangentMode
    0.72
    Geplaatst
    0.72
    DispatchToProps
    0.71
    Activations Density 0.002%

    No Known Activations