© 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. 0-CLT-HP
    4. 38462
    Prev
    Next
    INDEX
    Explanations

    hues

    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
     ordinaires
    -0.62
     hues
    -0.60
     LUMP
    -0.59
     juridiques
    -0.58
     riuscito
    -0.55
     financières
    -0.55
     chré
    -0.54
     ouverts
    -0.54
    ⓘ
    -0.54
     numériques
    -0.53
    POSITIVE LOGITS
    GEBURTSDATUM
    0.72
     propOrder
    0.62
    fjspx
    0.61
    تقاوى
    0.59
    RenderAtEndOf
    0.58
    SourceChecksum
    0.57
     ***!
    0.57
    Xna
    0.56
    TagMode
    0.55
    ReusableCell
    0.55
    Activations Density 0.063%

    No Known Activations