© 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. 0-CLT-HP
    7. 43232
    Prev
    Next
    INDEX
    Explanations

    ie

    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
    ie
    -1.80
    IE
    -1.16
     ie
    -1.02
     official
    -0.99
    Official
    -0.78
     IE
    -0.75
    ieme
    -0.74
     OFFICIAL
    -0.73
     officially
    -0.71
     Official
    -0.68
    POSITIVE LOGITS
    StateToProps
    0.57
     esboço
    0.57
     disambiguazione
    0.52
     snippetHide
    0.52
     futu
    0.51
    îtra
    0.49
     ExecuteAsync
    0.49
     apla
    0.49
    ToProps
    0.48
    __":
    0.48
    Activations Density 0.341%

    No Known Activations