© 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. 1561
    Prev
    Next
    INDEX
    Explanations

    chocolate

    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
     Chocolate
    -1.75
     chocolate
    -1.73
    chocolate
    -1.67
    Chocolate
    -1.64
     choco
    -1.30
     chocol
    -1.29
     chocolat
    -1.21
     chocolates
    -1.17
     шоколад
    -1.05
    OCOLATE
    -1.04
    POSITIVE LOGITS
    ism
    0.57
    ine
    0.56
     bar
    0.52
     is
    0.50
     in
    0.49
    ally
    0.48
     Con
    0.44
     pieces
    0.44
    y
    0.43
     block
    0.43
    Activations Density 0.427%

    No Known Activations