© 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. 4883
    Prev
    Next
    INDEX
    Explanations

    kids

    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
     Obrador
    -0.71
     مشين
    -0.68
    ValueStyle
    -0.57
    esModule
    -0.56
     hemorrhage
    -0.53
    MLLoader
    -0.52
    出版年
    -0.52
     CURIAM
    -0.50
    WriteTagHelper
    -0.50
    EndInit
    -0.50
    POSITIVE LOGITS
     gotta
    0.56
    club
    0.54
     stuff
    0.54
    holtz
    0.53
    health
    0.52
     Kamp
    0.52
    Kon
    0.51
     Kor
    0.51
     Klub
    0.51
    rule
    0.50
    Activations Density 0.004%

    No Known Activations