© 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. 1410
    Prev
    Next
    INDEX
    Explanations

    nuclear

    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
    ArrowToggle
    -1.03
     lenker
    -0.95
    IContainer
    -0.90
    RegressionTest
    -0.90
    참고
    -0.87
    marshaller
    -0.82
    astéroïdes
    -0.82
    TintMode
    -0.79
     Allociné
    -0.78
    GenerationType
    -0.77
    POSITIVE LOGITS
    сяг
    0.43
     I
    0.42
     techo
    0.42
    ity
    0.40
     http
    0.40
     der
    0.40
    med
    0.40
     when
    0.39
     faster
    0.39
    ndor
    0.39
    Activations Density 0.285%

    No Known Activations