© 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. 20-CLT-HP
    7. 71809
    Prev
    Next
    INDEX
    Explanations

    obese

    np_max-act-logits · 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
     CURIAM
    -0.73
    usermodel
    -0.70
    ContentAsync
    -0.68
    XmlAccessorType
    -0.68
    WaitGroup
    -0.65
    ⇑
    -0.65
    ArgumentParser
    -0.64
    AddTagHelper
    -0.63
     ExecuteAsync
    -0.63
    Datuak
    -0.61
    POSITIVE LOGITS
     out
    0.44
     obese
    0.42
    steamcommunity
    0.41
    Cast
    0.40
     porcelaine
    0.40
    Voci
    0.40
    springframework
    0.40
    scriptcase
    0.39
     thống
    0.39
     inductor
    0.39
    Activations Density 0.001%

    No Known Activations