© 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. 5-CLT-HP
    7. 4562
    Prev
    Next
    INDEX
    Explanations

    procedures or actions

    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
     Carta
    -0.53
    %";
    -0.50
     utafitiHapana
    -0.50
    ITERATURE
    -0.50
    nicity
    -0.50
     gepubliceerd
    -0.49
     Bekannt
    -0.47
    antigua
    -0.47
    %");
    -0.47
     rescat
    -0.47
    POSITIVE LOGITS
    balleur
    0.69
    +#+#
    0.63
     Parcelable
    0.58
    endregion
    0.57
    getWriter
    0.56
    pyplot
    0.56
     []:
    0.54
    richTextPanel
    0.54
     muualla
    0.54
     EconPapers
    0.53
    Activations Density 0.000%

    No Known Activations