© 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. 20-CLT-HP
    7. 77569
    Prev
    Next
    INDEX
    Explanations

    inch

    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
    yargs
    -0.52
    destroyAll
    -0.50
    boxes
    -0.49
    ganu
    -0.47
     Pole
    -0.47
    numerusform
    -0.46
    tubers
    -0.46
    #+#
    -0.45
    ioutil
    -0.45
    reactstrap
    -0.45
    POSITIVE LOGITS
    ConstraintMaker
    0.71
     <<<<<<<<<<<<<<
    0.69
    esModule
    0.63
     cast
    0.56
    IntoConstraints
    0.56
     MainAxisSize
    0.52
     Affiliations
    0.52
     spring
    0.50
    ))[
    0.49
     Spring
    0.48
    Activations Density 0.002%

    No Known Activations