© 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. 14904
    Prev
    Next
    INDEX
    Explanations

    Names

    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
     Ton
    -1.01
    Ton
    -0.71
    TagMode
    -0.56
     resourceCulture
    -0.54
    URLException
    -0.52
    idated
    -0.51
     Kat
    -0.51
    WebMethod
    -0.49
    tonsoft
    -0.49
    couragement
    -0.48
    POSITIVE LOGITS
    \{\\
    0.75
    ImageContext
    0.58
     بيها
    0.55
    wpi
    0.52
    CrossRef
    0.52
    RenderAtEndOf
    0.51
     StatefulWidget
    0.51
     Wikispecies
    0.50
     kasarigan
    0.50
    ViewImports
    0.50
    Activations Density 0.080%

    No Known Activations