© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90496
    Prev
    Next
    INDEX
    Explanations

    illustrate, indicate

    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
     indicate
    -1.01
     indicates
    -0.85
    indicate
    -0.71
     illustrate
    -0.70
     indicated
    -0.63
     Indicates
    -0.63
     testify
    -0.60
    indicates
    -0.60
    Describe
    -0.60
     Page
    -0.59
    POSITIVE LOGITS
     how
    0.72
     useAppContext
    0.66
     the
    0.61
     that
    0.57
     why
    0.56
     betweenstory
    0.56
     GeoNames
    0.55
    ameters
    0.54
     whether
    0.53
     سكانية
    0.53
    Activations Density 0.049%

    No Known Activations