© 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. 76919
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    rawDesc
    -0.81
     nahilalakip
    -0.73
    Geplaatst
    -0.69
     Wicidata
    -0.65
    出版年
    -0.60
     yoox
    -0.59
     Lingu
    -0.59
    abestanden
    -0.58
     cucchiai
    -0.58
     propOrder
    -0.58
    POSITIVE LOGITS
     four
    0.60
    posedge
    0.52
    four
    0.52
     receptive
    0.51
     cuatro
    0.49
     quatro
    0.49
     Four
    0.48
     FOUR
    0.48
    四个
    0.47
    bisoft
    0.46
    Activations Density 0.000%

    No Known Activations