© 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. 43226
    Prev
    Next
    INDEX
    Explanations

    either

    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
     either
    -2.00
    either
    -1.61
    Either
    -1.56
     Either
    -1.51
     entweder
    -1.31
    要么
    -1.02
     enten
    -0.94
     либо
    -0.89
     whichever
    -0.63
    ITHER
    -0.63
    POSITIVE LOGITS
     Chwiliwch
    0.79
     صوتيه
    0.79
     بيها
    0.77
    awtextra
    0.77
     disambiguazione
    0.74
     utafitiHapana
    0.72
     Wicidata
    0.68
     AspNetCore
    0.68
     bezeichneter
    0.68
     autorytatywna
    0.68
    Activations Density 0.021%

    No Known Activations