© 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. 4-CLT-HP
    7. 599
    Prev
    Next
    INDEX
    Explanations

    separate

    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
     with
    -0.65
    理石
    -0.59
     souhaitez
    -0.57
    ,
    -0.56
     nationales
    -0.56
    setDo
    -0.54
    Identyfik
    -0.54
    '
    -0.53
    dives
    -0.53
     zwar
    -0.52
    POSITIVE LOGITS
    sizeCache
    0.56
     Efq
    0.54
    ]--;
    0.53
    CppCodeGen
    0.52
     protesters
    0.52
    UseVisualStyle
    0.50
    ppuden
    0.50
    Попис
    0.49
     LUZ
    0.48
    تقاوى
    0.48
    Activations Density 0.002%

    No Known Activations