© 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. 75488
    Prev
    Next
    INDEX
    Explanations

    arrangements and connections

    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
    lamabad
    -0.62
     estekak
    -0.61
    softc
    -0.56
    Jîn
    -0.52
     AspNetCore
    -0.49
     Italijanski
    -0.47
    ništ
    -0.46
    expandindo
    -0.46
    RegressionTest
    -0.45
     alimentazione
    -0.44
    POSITIVE LOGITS
    GraphicsUnit
    0.81
     radi
    0.60
     PDI
    0.56
    InputTagHelper
    0.56
     bid
    0.55
     merid
    0.55
     left
    0.54
     orth
    0.54
    ver
    0.53
    sequ
    0.53
    Activations Density 0.003%

    No Known Activations