© 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. 71884
    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
     AssemblyCompany
    -0.71
     Савезне
    -0.66
    ](#
    -0.65
    hoeddwyd
    -0.65
     समीक्षक
    -0.64
    adpleegd
    -0.62
    modelBuilder
    -0.60
    WithIOException
    -0.57
    errHandler
    -0.56
    دانشنامهٔ
    -0.56
    POSITIVE LOGITS
    makin
    0.50
    BITE
    0.48
    External
    0.48
    byr
    0.48
    bi
    0.48
     EXTERNAL
    0.47
    i
    0.47
    bis
    0.46
    ti
    0.46
    ipun
    0.46
    Activations Density 0.001%

    No Known Activations