© 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. 5-CLT-HP
    7. 509
    Prev
    Next
    INDEX
    Explanations

    business/commerce

    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
    enumi
    -0.71
     diversified
    -0.57
     diversify
    -0.56
     colorWith
    -0.52
     perpetual
    -0.51
     AssemblyCulture
    -0.51
    Ottimo
    -0.50
     diversi
    -0.49
     combineReducers
    -0.49
    timeter
    -0.48
    POSITIVE LOGITS
     OMITBAD
    0.69
     carico
    0.54
    addGap
    0.53
    
    0.52
     يتيمه
    0.50
    WithIOException
    0.48
     arbete
    0.48
    Grath
    0.46
     arbeta
    0.45
    driving
    0.44
    Activations Density 0.005%

    No Known Activations