© 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. 5-CLT-HP
    7. 97599
    Prev
    Next
    INDEX
    Explanations

    Code/Formal Writing

    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
    TagHelper
    -0.67
    RenderAtEndOf
    -0.65
    ConstraintMaker
    -0.64
    iconque
    -0.63
    TypedDataSet
    -0.63
    standers
    -0.63
    routeProvider
    -0.62
    tagHelperRunner
    -0.62
    /******/
    -0.62
    SerializedName
    -0.60
    POSITIVE LOGITS
     practice
    0.52
     being
    0.47
    mapTo
    0.46
     gouver
    0.46
     Practice
    0.45
     practicing
    0.45
     politics
    0.45
     service
    0.44
     PRACT
    0.42
     Industrie
    0.42
    Activations Density 0.004%

    No Known Activations