© 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. 1-CLT-HP
    7. 15540
    Prev
    Next
    INDEX
    Explanations

    brand

    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
     brand
    -1.23
    brand
    -1.19
     Brand
    -1.09
    Brand
    -1.03
     BRAND
    -0.96
    BRAND
    -0.93
     brands
    -0.87
    brands
    -0.86
    branding
    -0.80
    branded
    -0.72
    POSITIVE LOGITS
     NORM
    0.62
     contextLoads
    0.57
    templateUrl
    0.53
     desirability
    0.53
    styleUrls
    0.53
    arXiv
    0.52
     referenties
    0.52
     formations
    0.52
     habitation
    0.52
     mantra
    0.51
    Activations Density 0.018%

    No Known Activations