© 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. 91561
    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
    SequentialGroup
    -0.91
     EconPapers
    -0.77
    mergeFrom
    -0.75
     transférez
    -0.71
     Normdatei
    -0.70
    styleType
    -0.69
     beginnetje
    -0.69
    KommentareTeilen
    -0.69
    
    -0.68
     дописавши
    -0.67
    POSITIVE LOGITS
     Micho
    0.42
    weihnachts
    0.42
    TProtocol
    0.39
     Galileo
    0.38
    leş
    0.38
     Barnabas
    0.36
     typename
    0.36
     cartaz
    0.36
     AttributeSet
    0.35
     enc
    0.35
    Activations Density 0.003%

    No Known Activations