© 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. 71955
    Prev
    Next
    INDEX
    Explanations

    Code and math 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
     initComponents
    -0.75
    enterOuterAlt
    -0.64
    ➞
    -0.63
    ffindor
    -0.60
    ništvo
    -0.60
     gawas
    -0.56
    Искәрмәләр
    -0.56
    êques
    -0.55
    $+$
    -0.54
    +
    -0.54
    POSITIVE LOGITS
     looked
    0.69
    looked
    0.66
     Looked
    0.51
    WebServlet
    0.50
    LOOK
    0.49
     look
    0.49
    LAC
    0.47
     molta
    0.46
    Look
    0.45
    maßen
    0.45
    Activations Density 0.000%

    No Known Activations