© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75655
    Prev
    Next
    INDEX
    Explanations

    Marketing and business

    np_max-act-logits · 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
    Marketing
    -1.27
     Marketing
    -1.15
     MARKETING
    -1.11
    Market
    -1.11
     Market
    -1.06
    MARKETING
    -1.02
     MARKET
    -0.99
    marketing
    -0.95
    MARKET
    -0.89
     kasarigan
    -0.88
    POSITIVE LOGITS
    EndContext
    0.66
    abestanden
    0.45
    orm
    0.42
    4
    0.40
     sem
    0.40
    kk
    0.38
     Go
    0.36
    ues
    0.36
     B
    0.36
     m
    0.35
    Activations Density 0.003%

    No Known Activations