© 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. 5-CLT-HP
    7. 4163
    Prev
    Next
    INDEX
    Explanations

    code returns

    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
    localctx
    -0.54
    exitRule
    -0.52
    sedown
    -0.51
     Insee
    -0.47
    IsInitialized
    -0.47
    autorest
    -0.45
    research
    -0.44
     cote
    -0.43
    SaveVideo
    -0.43
    testify
    -0.43
    POSITIVE LOGITS
    eting
    0.78
    ंदीखरीदारी
    0.70
    expandindo
    0.66
    CreateMap
    0.66
     numerus
    0.64
    licting
    0.56
    脚注の使い方
    0.55
     StatefulWidget
    0.55
    pearing
    0.54
    ening
    0.54
    Activations Density 0.007%

    No Known Activations