© 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. 1-CLT-HP
    7. 14911
    Prev
    Next
    INDEX
    Explanations

    Paul

    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
     Paul
    -1.27
     paul
    -1.17
    Paul
    -1.09
    paul
    -1.06
     PAUL
    -1.02
    PAUL
    -0.93
    ポール
    -0.65
     Paulus
    -0.62
     Pau
    -0.59
     Audiodateien
    -0.52
    POSITIVE LOGITS
     propOrder
    1.12
    NOPQRST
    0.78
    HtmlAttribute
    0.66
    TagMode
    0.60
     Methuen
    0.60
     AssemblyCulture
    0.59
     Soccerway
    0.58
     Huguen
    0.57
    LEncoder
    0.57
    verwijspagina
    0.57
    Activations Density 0.031%

    No Known Activations