© 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. 0-CLT-HP
    7. 94741
    Prev
    Next
    INDEX
    Explanations

    fewer

    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
     fewer
    -1.23
     links
    -1.08
    links
    -0.95
    bu
    -0.86
     Links
    -0.84
     LINKS
    -0.83
     Fewer
    -0.81
    Links
    -0.77
     bu
    -0.71
    LINKS
    -0.69
    POSITIVE LOGITS
     resourceCulture
    0.83
    yntaxException
    0.79
    writeFieldEnd
    0.79
    RegressionTest
    0.77
    sizeCache
    0.76
    SourceChecksum
    0.75
     propOrder
    0.74
    izophrenia
    0.73
     Roskov
    0.73
     Réponses
    0.71
    Activations Density 0.200%

    No Known Activations