© 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. 92277
    Prev
    Next
    INDEX
    Explanations

    Applying substances to surfaces

    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
     coat
    -0.89
    coat
    -0.78
     Coat
    -0.65
    cki
    -0.57
    co
    -0.56
     côtés
    -0.56
    elaar
    -0.54
     industriels
    -0.52
     craindre
    -0.52
     coats
    -0.52
    POSITIVE LOGITS
     Roskov
    0.98
     propOrder
    0.84
    packer
    0.80
    oredCriteria
    0.79
    脚注の使い方
    0.78
    SharedDtor
    0.77
    setVerticalGroup
    0.75
    parsedMessage
    0.75
    e
    0.73
    Zacks
    0.72
    Activations Density 0.051%

    No Known Activations