© 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. 94455
    Prev
    Next
    INDEX
    Explanations

    has

    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
     AssemblyProduct
    -0.67
     TextInputType
    -0.65
    bnf
    -0.64
    RenderAtEndOf
    -0.63
    WebVitals
    -0.63
    kjø
    -0.62
     amoureux
    -0.61
    السكان
    -0.60
    łoś
    -0.60
    ariato
    -0.60
    POSITIVE LOGITS
     we
    0.48
    Наводи
    0.47
    Referències
    0.47
    はじめに
    0.47
    Referencies
    0.46
     once
    0.43
     hatten
    0.43
     down
    0.43
     start
    0.43
     suy
    0.42
    Activations Density 0.015%

    No Known Activations