© 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. 0-CLT-HP
    7. 41288
    Prev
    Next
    INDEX
    Explanations

    site

    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
     site
    -0.82
    site
    -0.75
     sites
    -0.69
     Site
    -0.59
    Site
    -0.56
     sito
    -0.48
     SITE
    -0.48
     वे
    -0.47
    网站
    -0.46
     سایت
    -0.46
    POSITIVE LOGITS
     كومونز
    0.78
    MLLoader
    0.77
    UIControlState
    0.71
    WriteTagHelper
    0.71
     للمعارف
    0.71
     استنادى
    0.70
     noDo
    0.69
     TextInputType
    0.69
    SequentialGroup
    0.67
     оригіналу
    0.67
    Activations Density 0.068%

    No Known Activations