© 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. 1-CLT-HP
    7. 14635
    Prev
    Next
    INDEX
    Explanations

    Days off/specific days

    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
    tagHelperRunner
    -0.62
    ostante
    -0.57
    μιουργ
    -0.55
     Akismet
    -0.54
    structors
    -0.53
     glyphicon
    -0.52
    ternut
    -0.51
    shutterstock
    -0.50
    ^(@)
    -0.50
    yng
    -0.50
    POSITIVE LOGITS
    principalTable
    0.50
    AntiForgeryToken
    0.49
    WireFormatLite
    0.49
     Federated
    0.46
     AFC
    0.45
    waitKey
    0.45
    TestRunner
    0.45
    baran
    0.44
     STC
    0.44
    δικ
    0.44
    Activations Density 0.115%

    No Known Activations