© 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. 2605
    Prev
    Next
    INDEX
    Explanations

    more

    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
     مشين
    -0.75
     autorytatywna
    -0.72
    Diwedd
    -0.71
    RegressionTest
    -0.66
     nahilalakip
    -0.60
     ویکی‌پدیای
    -0.59
    AddTagHelper
    -0.57
     descendre
    -0.57
     esternos
    -0.57
     Chwiliwch
    -0.56
    POSITIVE LOGITS
     Morm
    0.50
     Tch
    0.46
    Portale
    0.44
     Nadu
    0.44
     QtCore
    0.44
    sit
    0.44
    runs
    0.44
    ranath
    0.43
     Art
    0.43
     Nation
    0.43
    Activations Density 0.003%

    No Known Activations