© 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. 4-CLT-HP
    7. 713
    Prev
    Next
    INDEX
    Explanations

    business and 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
     مرئيه
    -0.71
    principalColumn
    -0.70
    RetentionPolicy
    -0.60
    WebElementEntity
    -0.59
    kháu
    -0.56
    )__
    -0.54
    uvre
    -0.54
     Grind
    -0.54
    cedes
    -0.52
    굴
    -0.51
    POSITIVE LOGITS
    <bos>
    0.81
     архивлан
    0.56
    reactstrap
    0.51
     autorytatywna
    0.50
     HttpNotFound
    0.47
    LayoutPanel
    0.47
    cticut
    0.46
    AndEndTag
    0.44
     clínicas
    0.44
    Businesses
    0.44
    Activations Density 0.011%

    No Known Activations