© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5073
    Prev
    Next
    INDEX
    Explanations

    location and measurements

    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
    Normdaten
    -0.55
    ArrowToggle
    -0.52
    dataclass
    -0.52
    BeginContext
    -0.52
    RunAsync
    -0.51
    PointerException
    -0.50
     nhật
    -0.50
    NewGuid
    -0.49
     charging
    -0.49
    FormTagHelper
    -0.49
    POSITIVE LOGITS
    новниш
    0.59
    OGND
    0.56
     disambiguazione
    0.55
    tween
    0.52
    Begriffsklä
    0.50
     plages
    0.49
     désolés
    0.48
     gâ
    0.47
     characterised
    0.47
    ؤلاء
    0.47
    Activations Density 0.003%

    No Known Activations