© 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. 5-CLT-HP
    7. 5058
    Prev
    Next
    INDEX
    Explanations

    code/legal documents

    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
     للاسماء
    -0.54
    новништво
    -0.50
     habet
    -0.47
    extAlignment
    -0.46
     distanciation
    -0.46
    writeField
    -0.46
     rowspan
    -0.44
    lapsingToolbar
    -0.43
    tské
    -0.42
     saja
    -0.42
    POSITIVE LOGITS
    رشف
    0.60
    adaptiveStyles
    0.60
    Personensuche
    0.59
    yarnpkg
    0.58
    CppCodeGen
    0.57
    (||
    0.55
    adays
    0.54
    iocene
    0.54
     catalog
    0.53
    økt
    0.53
    Activations Density 0.015%

    No Known Activations