© 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. 0-CLT-HP
    7. 94733
    Prev
    Next
    INDEX
    Explanations

    descriptions

    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
     المعيارى
    -0.80
     EconPapers
    -0.77
    parsedMessage
    -0.71
     <=",
    -0.70
     NUKAT
    -0.65
    adaptiveStyles
    -0.63
    styleType
    -0.63
    istoitu
    -0.63
    jspb
    -0.60
     unknownFields
    -0.60
    POSITIVE LOGITS
    boards
    0.60
     tori
    0.60
     dynasties
    0.60
     revolutionaries
    0.59
    ifiers
    0.59
     snuff
    0.57
     catalogues
    0.55
     Whigs
    0.55
    mayın
    0.54
     Attila
    0.54
    Activations Density 0.140%

    No Known Activations