© 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. 45481
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous news

    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
     quiet
    -0.86
     popular
    -0.73
    quiet
    -0.72
    Quiet
    -0.69
     quieter
    -0.69
    popular
    -0.68
     Quiet
    -0.66
    Popular
    -0.61
    soft
    -0.60
     Popular
    -0.59
    POSITIVE LOGITS
     pleaſure
    0.71
    LookAnd
    0.67
     uſed
    0.66
     beſt
    0.66
    AsUp
    0.65
    SharedDtor
    0.64
    StoryboardSegue
    0.64
    abestanden
    0.62
    neſs
    0.62
    adpleegd
    0.61
    Activations Density 0.054%

    No Known Activations