© 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. 0-CLT-HP
    7. 41645
    Prev
    Next
    INDEX
    Explanations

    definitions and actions

    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
     Standing
    -0.53
     đối
    -0.52
    Filler
    -0.50
     standing
    -0.48
     presenters
    -0.48
     afili
    -0.48
    Standing
    -0.47
    DeleteBehavior
    -0.47
     weighs
    -0.47
     cool
    -0.47
    POSITIVE LOGITS
    WebElementEntity
    0.81
    findpost
    0.70
    出版年
    0.70
     contextLoads
    0.68
    tagext
    0.68
     asyncio
    0.66
     autrement
    0.66
    Xna
    0.64
     StringTokenizer
    0.64
     bénéfices
    0.62
    Activations Density 0.662%

    No Known Activations