© 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. 4-CLT-HP
    7. 1092
    Prev
    Next
    INDEX
    Explanations

    the

    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
    StoryboardSegue
    -0.73
     CreateTagHelper
    -0.71
    criptors
    -0.65
    icestershire
    -0.63
     dialects
    -0.63
    <bos>
    -0.63
     niches
    -0.63
     elevations
    -0.63
     tributaries
    -0.62
     dummies
    -0.62
    POSITIVE LOGITS
     formidable
    0.57
     popular
    0.54
     acer
    0.52
     remarkably
    0.51
     highly
    0.50
     noted
    0.50
     remarkable
    0.50
     brilliant
    0.50
     (
    0.49
     wise
    0.49
    Activations Density 0.002%

    No Known Activations