© 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. 43639
    Prev
    Next
    INDEX
    Explanations

    excerpts

    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
     Excerpt
    -0.75
     feature
    -0.73
     Feature
    -0.72
    Билгалдахарш
    -0.71
     excerpt
    -0.71
     summarize
    -0.70
    ніципалі
    -0.64
    Feature
    -0.63
    enumi
    -0.63
     summarizing
    -0.63
    POSITIVE LOGITS
    ised
    0.69
    ized
    0.63
    ization
    0.59
    izer
    0.59
    izes
    0.58
    sive
    0.57
    izing
    0.56
     CreateTagHelper
    0.54
    setof
    0.50
    duğu
    0.49
    Activations Density 0.224%

    No Known Activations