© 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. 1-CLT-HP
    7. 14727
    Prev
    Next
    INDEX
    Explanations

    code and data

    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
     epoch
    -1.85
     Epoch
    -1.65
    epoch
    -1.51
    Epoch
    -1.48
     epochs
    -1.29
    EPO
    -0.87
    epochs
    -0.86
     EPO
    -0.82
     epo
    -0.63
    Rcpp
    -0.57
    POSITIVE LOGITS
    al
    0.93
    ally
    0.58
    alism
    0.57
    ️
    0.57
    almente
    0.57
    AL
    0.57
    icity
    0.56
    ︎
    0.53
    ים
    0.52
    alni
    0.51
    Activations Density 0.009%

    No Known Activations