© 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. 10386
    Prev
    Next
    INDEX
    Explanations

    body

    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
    AnchorStyles
    -0.43
     تضيفلها
    -0.42
    PerformLayout
    -0.40
    theless
    -0.40
     bonté
    -0.39
    cartão
    -0.39
    Morfologia
    -0.38
     समीक्षाओं
    -0.37
    FormTagHelper
    -0.37
     Amérique
    -0.37
    POSITIVE LOGITS
    PHeader
    0.64
     ModelExpression
    0.62
    ->_
    0.61
    PointerException
    0.61
    Tikang
    0.60
    ocardium
    0.59
    AddHtmlAttribute
    0.59
    liothè
    0.59
     LIBR
    0.58
     ProtoMessage
    0.57
    Activations Density 0.023%

    No Known Activations