© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13510
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ThroughAttribute
    -0.79
    AnchorStyles
    -0.70
     MainAxisSize
    -0.69
     sanguí
    -0.69
    WriteBarrier
    -0.67
     BoxFit
    -0.65
     CreateTagHelper
    -0.62
    bootstrapcdn
    -0.60
    NOPQRST
    -0.60
    पया
    -0.60
    POSITIVE LOGITS
    Viited
    0.54
    }:${
    0.45
     Liber
    0.43
     Clos
    0.43
    ')(
    0.43
     CW
    0.42
     report
    0.42
    Biographie
    0.42
     sub
    0.41
     record
    0.41
    Activations Density 0.074%

    No Known Activations