© 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. 579
    Prev
    Next
    INDEX
    Explanations

    to

    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
    :✨
    -0.85
    انيف
    -0.83
     /\.(
    -0.82
    RegressionTest
    -0.80
    ंदीखरीदारी
    -0.78
    MigrationBuilder
    -0.77
     <<<<<<<<<<<<<<
    -0.77
     للاسماء
    -0.77
     يتيمه
    -0.76
     שוליים
    -0.76
    POSITIVE LOGITS
     see
    0.79
     experience
    0.75
     watch
    0.65
     reflect
    0.61
     choose
    0.60
     enjoy
    0.59
     count
    0.58
     witness
    0.57
     expose
    0.57
     try
    0.56
    Activations Density 0.010%

    No Known Activations