© 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. 4-CLT-HP
    7. 2042
    Prev
    Next
    INDEX
    Explanations

    cosa

    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
    Autoritní
    -0.87
    المناصب
    -0.85
     المعيارى
    -0.75
    URLException
    -0.74
     мәкал
    -0.72
     فريبيس
    -0.71
     CreateTagHelper
    -0.70
    ViewImports
    -0.68
    MLLoader
    -0.68
    ViewFeatures
    -0.66
    POSITIVE LOGITS
     a
    0.58
     been
    0.53
    jasmine
    0.46
     tested
    0.46
     an
    0.46
     exhibited
    0.45
     shown
    0.44
     indexed
    0.44
     ouder
    0.44
     responsive
    0.43
    Activations Density 0.006%

    No Known Activations