© 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. 713
    Prev
    Next
    INDEX
    Explanations

    better

    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
    QMetaType
    -0.56
    ViewStyle
    -0.52
     kasarigan
    -0.52
    ScopeManager
    -0.51
    ContentAsync
    -0.49
    MessageOf
    -0.48
    født
    -0.48
     Paglinawan
    -0.48
     SIO
    -0.46
    Personendaten
    -0.45
    POSITIVE LOGITS
    XmlAccessType
    0.59
    lewati
    0.57
    INCLUDES
    0.57
     beweging
    0.56
     päät
    0.56
    engkapi
    0.56
     oplossing
    0.56
     selection
    0.54
     uitzicht
    0.54
    Здра
    0.54
    Activations Density 0.032%

    No Known Activations