© 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. 38306
    Prev
    Next
    INDEX
    Explanations

    commercial/clinical

    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
     commercial
    -2.14
    commercial
    -1.99
    Commercial
    -1.91
     Commercial
    -1.79
     COMMERCIAL
    -1.76
     commercially
    -1.69
     comerciales
    -1.63
     clinical
    -1.61
     commerciale
    -1.60
     commerciaux
    -1.57
    POSITIVE LOGITS
    ization
    0.84
    ised
    0.62
    ized
    0.59
    izing
    0.54
    isation
    0.53
    DoubleQuotes
    0.52
    ity
    0.52
    ities
    0.52
    KURZBESCHREIBUNG
    0.50
    izable
    0.47
    Activations Density 0.813%

    No Known Activations