© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 76028
    Prev
    Next
    INDEX
    Explanations

    code, math

    np_max-act-logits · 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
    Cleared
    -0.63
     inalámb
    -0.53
    adal
    -0.53
     Clean
    -0.52
     inalámbrica
    -0.51
     Diſ
    -0.51
    concep
    -0.49
     limpi
    -0.49
     Stabilization
    -0.49
    KEA
    -0.48
    POSITIVE LOGITS
     lots
    0.63
    argout
    0.61
     more
    0.57
    UserScript
    0.57
     numberOfRows
    0.55
     plenty
    0.54
     spots
    0.53
    windowFixed
    0.53
     times
    0.52
     loads
    0.52
    Activations Density 0.001%

    No Known Activations