© 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. 5230
    Prev
    Next
    INDEX
    Explanations

    increases

    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
    ValueStyle
    -0.73
    ConstraintMaker
    -0.72
    клопе
    -0.69
     FetchType
    -0.65
    Again
    -0.62
    Filmografie
    -0.61
     MainAxisSize
    -0.61
     متعلقه
    -0.59
     Again
    -0.58
    CloseOperation
    -0.57
    POSITIVE LOGITS
    enaars
    0.48
    ườ
    0.44
    untur
    0.44
    haca
    0.44
    üyada
    0.44
    assertRaises
    0.43
    inema
    0.43
    erals
    0.42
    lorus
    0.41
    usschuss
    0.41
    Activations Density 0.002%

    No Known Activations