© 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. 77420
    Prev
    Next
    INDEX
    Explanations

    distribution

    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
     supérieures
    -0.67
     AssemblyCulture
    -0.65
     avoient
    -0.65
     Theſe
    -0.63
     soggior
    -0.62
     referenties
    -0.62
    DeleteBehavior
    -0.62
     Vordergrund
    -0.61
    intenant
    -0.61
     zubehör
    -0.60
    POSITIVE LOGITS
     distributed
    1.09
     scattered
    1.00
     spread
    0.96
     dispersed
    0.96
     dotted
    0.95
     pepper
    0.86
     dot
    0.82
     spaced
    0.79
     evenly
    0.79
     sprinkled
    0.78
    Activations Density 0.004%

    No Known Activations