© 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. 94880
    Prev
    Next
    INDEX
    Explanations

    also

    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
    ing
    -0.61
     generalize
    -0.59
    ResponseStatus
    -0.57
    clude
    -0.57
     وتسجيلات
    -0.57
     continue
    -0.56
     displace
    -0.55
     begin
    -0.55
     enumerate
    -0.55
    itized
    -0.54
    POSITIVE LOGITS
    IUrlHelper
    0.89
     applies
    0.69
     has
    0.67
     happens
    0.66
     contains
    0.66
     ComVisible
    0.63
     leads
    0.62
     fits
    0.61
     occurs
    0.60
     determines
    0.60
    Activations Density 0.096%

    No Known Activations