© 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. 5-CLT-HP
    7. 94099
    Prev
    Next
    INDEX
    Explanations

    Code/Log snippets

    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
     note
    -0.61
     image
    -0.57
     sign
    -0.57
     notes
    -0.52
     read
    -0.52
    note
    -0.50
     text
    -0.50
     contents
    -0.48
     feeling
    -0.48
     page
    -0.48
    POSITIVE LOGITS
    PreferredItem
    0.73
    MigrationBuilder
    0.72
    iecie
    0.71
     tramonto
    0.68
    resizingMask
    0.66
     pioggia
    0.64
     courir
    0.63
     gomma
    0.63
     spesa
    0.62
     paesaggio
    0.62
    Activations Density 0.001%

    No Known Activations