© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 246
    Prev
    Next
    INDEX
    Explanations

    culture

    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
     of
    -0.52
    roek
    -0.44
    -
    -0.42
    chaffenheit
    -0.40
    for
    -0.40
    ///</
    -0.39
    case
    -0.39
    дым
    -0.39
    street
    -0.38
     abgeschlossen
    -0.38
    POSITIVE LOGITS
    ագրություններ
    0.81
    ɵɵelementStart
    0.74
    NUMX
    0.74
     wickets
    0.72
    AnchorStyles
    0.71
    IntoConstraints
    0.70
    IonicModule
    0.68
     oars
    0.67
    AnimationsModule
    0.67
    ThemeOverlay
    0.66
    Activations Density 0.002%

    No Known Activations