© 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. 15000
    Prev
    Next
    INDEX
    Explanations

    personal care products

    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
     toothpaste
    -1.75
    XmlAccessType
    -0.73
     Tooth
    -0.72
     CreateTagHelper
    -0.71
    Tooth
    -0.68
     tooth
    -0.68
    tooth
    -0.66
     mennes
    -0.64
    adeloupe
    -0.62
     mennesker
    -0.60
    POSITIVE LOGITS
    IUrlHelper
    0.64
    AddHtmlAttribute
    0.54
    InputTagHelper
    0.52
    PyTuple
    0.52
    AccessorTable
    0.49
    e
    0.49
     оригіналу
    0.49
    DoubleQuotes
    0.48
    pters
    0.47
     createState
    0.47
    Activations Density 0.006%

    No Known Activations