© 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. 4-CLT-HP
    7. 2729
    Prev
    Next
    INDEX
    Explanations

    clothing

    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
     möjlighet
    -0.58
     puits
    -0.52
     autón
    -0.51
     regionales
    -0.51
    holo
    -0.51
     cláus
    -0.50
     förr
    -0.50
    árny
    -0.49
    Enumerated
    -0.48
     soulign
    -0.47
    POSITIVE LOGITS
     jacket
    0.71
     Wikimedijinoj
    0.67
    jacket
    0.63
    shirts
    0.62
     jackets
    0.60
     calendriers
    0.59
    shirt
    0.59
     worn
    0.59
     shirt
    0.59
     dress
    0.58
    Activations Density 0.034%

    No Known Activations