© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94125
    Prev
    Next
    INDEX
    Explanations

    business/finance

    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
     revenue
    -1.42
    revenue
    -1.42
    Revenue
    -1.40
     Revenue
    -1.34
     Revenues
    -1.21
     Income
    -1.17
    Income
    -1.17
     income
    -1.15
     INCOME
    -1.10
     revenues
    -1.07
    POSITIVE LOGITS
    e
    0.67
    i
    0.55
    es
    0.54
    to
    0.51
    -
    0.50
     panel
    0.49
    y
    0.48
    h
    0.47
    ;
    0.47
    ed
    0.46
    Activations Density 0.091%

    No Known Activations