© 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. 90780
    Prev
    Next
    INDEX
    Explanations

    diagram

    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
     diagram
    -0.74
    ArrowToggle
    -0.69
     defaultstate
    -0.64
    s
    -0.61
    Rüyada
    -0.59
     schematic
    -0.57
    RegistryLite
    -0.54
    Diagram
    -0.53
     ProtoMessage
    -0.52
    scheme
    -0.52
    POSITIVE LOGITS
    mer
    0.71
    berley
    0.63
    mers
    0.60
    lem
    0.57
    bye
    0.57
    teen
    0.56
    glie
    0.56
    mazione
    0.55
    gn
    0.54
    MER
    0.54
    Activations Density 0.059%

    No Known Activations