© 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. 5-CLT-HP
    7. 5850
    Prev
    Next
    INDEX
    Explanations

    credit card fraud

    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
    apimachinery
    -0.69
    Демографія
    -0.65
    webElementXpaths
    -0.65
    xodo
    -0.64
    省市镇
    -0.63
    TypedDataSet
    -0.61
    yntaxException
    -0.60
    verifyException
    -0.60
     bpy
    -0.60
     fraî
    -0.59
    POSITIVE LOGITS
    ivasan
    0.54
     afterward
    0.49
     thereafter
    0.49
    later
    0.47
     afterwards
    0.47
    leyebilirsiniz
    0.45
     later
    0.44
     Afterward
    0.43
    ilding
    0.43
    ldorf
    0.43
    Activations Density 0.001%

    No Known Activations