© 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. 4203
    Prev
    Next
    INDEX
    Explanations

    smell

    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
    MigrationBuilder
    -0.56
    complexContent
    -0.55
    addContainerGap
    -0.55
    holdet
    -0.52
     CreateTagHelper
    -0.52
    Against
    -0.50
    LookAnd
    -0.50
     kasarigan
    -0.49
    ArgsConstructor
    -0.47
     acceptez
    -0.47
    POSITIVE LOGITS
     of
    0.84
     BoxDecoration
    0.62
    RectangleBorder
    0.60
     that
    0.58
     trajets
    0.56
     between
    0.55
    SharedDtor
    0.54
    ptid
    0.53
    XDECREF
    0.52
     BoxFit
    0.52
    Activations Density 0.001%

    No Known Activations