© 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. 20-CLT-HP
    7. 71766
    Prev
    Next
    INDEX
    Explanations

    website/code content

    np_max-act-logits · 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
     EconPapers
    -0.56
    AndEndTag
    -0.55
    Rest
    -0.50
    GHI
    -0.49
    ➞
    -0.48
     narrated
    -0.47
    WebElementEntity
    -0.46
     surla
    -0.46
    uitable
    -0.46
    Personensuche
    -0.44
    POSITIVE LOGITS
    forName
    0.59
    edicated
    0.57
    usepackage
    0.57
    onViewCreated
    0.57
    withIdentifier
    0.56
     analysis
    0.56
    struts
    0.56
     '\\;'
    0.55
    ValueStyle
    0.55
    ANALYSIS
    0.54
    Activations Density 0.000%

    No Known Activations