© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73517
    Prev
    Next
    INDEX
    Explanations

    Code/technical 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
    explique
    -0.56
    
    -0.52
    Espèce
    -0.49
    pensive
    -0.49
     atheist
    -0.49
     EClass
    -0.48
     Tiberius
    -0.47
    cshtml
    -0.44
     celib
    -0.43
    bw
    -0.43
    POSITIVE LOGITS
    IsMutable
    0.63
     ویکی‌پدیا
    0.62
    #+#
    0.58
    ⮕
    0.54
    Carriera
    0.53
     tramp
    0.52
    rrggbb
    0.52
     Seitz
    0.52
     possano
    0.50
     opérés
    0.50
    Activations Density 0.000%

    No Known Activations