© 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. 0-CLT-HP
    7. 42829
    Prev
    Next
    INDEX
    Explanations

    technical/abstract language

    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
    sive
    -1.07
    sion
    -1.02
    sions
    -0.99
    iting
    -0.79
    uding
    -0.77
    sioni
    -0.68
    ITING
    -0.63
    sión
    -0.63
     remained
    -0.60
     fossils
    -0.59
    POSITIVE LOGITS
    InteropServices
    0.69
     ExecuteAsync
    0.67
     Préférences
    0.59
     layui
    0.54
    condido
    0.53
    кономі
    0.51
    GMENT
    0.50
    alkin
    0.50
     sheets
    0.49
    ConstraintMaker
    0.49
    Activations Density 1.281%

    No Known Activations