© 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. 20-CLT-HP
    7. 76571
    Prev
    Next
    INDEX
    Explanations

    scientific/technical texts

    np_max-act-logits · 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
    TypedDataSet
    -0.58
    RenderAtEndOf
    -0.52
     NDEBUG
    -0.50
    GTCX
    -0.48
     ujednoznacz
    -0.48
     XCTest
    -0.47
     Exactos
    -0.47
     Exacts
    -0.45
     فريبيس
    -0.44
    ENSA
    -0.44
    POSITIVE LOGITS
     down
    0.67
     up
    0.65
     trans
    0.57
    kopf
    0.57
     Up
    0.56
    NgModule
    0.54
     Down
    0.54
     footprints
    0.53
     createState
    0.52
    down
    0.51
    Activations Density 0.000%

    No Known Activations