© 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. 1-CLT-HP
    7. 45903
    Prev
    Next
    INDEX
    Explanations

    scattered

    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
     spread
    -0.65
    spread
    -0.62
    sizeCache
    -0.57
     Autorizaciones
    -0.56
    ReusableCell
    -0.54
    Hose
    -0.52
    ExtendWith
    -0.50
    IntoConstraints
    -0.49
     Spread
    -0.49
    Spread
    -0.48
    POSITIVE LOGITS
     كومونز
    0.59
    igslist
    0.49
     AssemblyCompany
    0.49
    PreExecute
    0.49
    runApp
    0.49
     COMMENTS
    0.48
     Mert
    0.48
     cowl
    0.47
    ouds
    0.47
    sels
    0.47
    Activations Density 0.005%

    No Known Activations