© 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. 38613
    Prev
    Next
    INDEX
    Explanations

    fruit or beach

    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
     fruits
    -2.08
     fruit
    -2.02
     Fruit
    -1.83
     FRUIT
    -1.80
     Fruits
    -1.79
    fruit
    -1.77
    fruits
    -1.72
    Fruit
    -1.70
    Fruits
    -1.44
     fruta
    -1.24
    POSITIVE LOGITS
    line
    0.57
    web
    0.50
    Line
    0.48
    ing
    0.47
    لينكات
    0.46
    fulness
    0.44
    row
    0.44
    ériale
    0.43
    WEB
    0.42
    ted
    0.41
    Activations Density 0.368%

    No Known Activations