© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93347
    Prev
    Next
    INDEX
    Explanations

    Publishing

    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
     larmes
    -0.69
     extérieure
    -0.57
     épaules
    -0.56
     genoux
    -0.56
     boî
    -0.55
     églises
    -0.53
     colorés
    -0.53
    RunAsync
    -0.52
     alimentaires
    -0.51
    orari
    -0.51
    POSITIVE LOGITS
    IComponent
    0.65
     clubs
    0.63
     acc
    0.56
    TextHelper
    0.56
    RegistryLite
    0.54
     Kopp
    0.54
    Демографія
    0.54
     lys
    0.54
    @[+][
    0.54
     combos
    0.52
    Activations Density 0.110%

    No Known Activations