© 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. 4-CLT-HP
    7. 4786
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     food
    -0.87
    food
    -0.79
     FOOD
    -0.62
     comida
    -0.60
    FOOD
    -0.59
     voedsel
    -0.58
     cibo
    -0.57
     dietary
    -0.57
     nourriture
    -0.57
     alimentaire
    -0.56
    POSITIVE LOGITS
     متعلقه
    0.78
    AccessorTable
    0.68
    GeneratedValue
    0.67
     Савезне
    0.66
    <bos>
    0.65
    Искәрмәләр
    0.64
     gynhyrchwyd
    0.63
    orElseThrow
    0.63
     invokingState
    0.63
    protoimpl
    0.62
    Activations Density 0.000%

    No Known Activations