© 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. 93296
    Prev
    Next
    INDEX
    Explanations

    question prompts

    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
     future
    -1.10
    future
    -1.09
    Future
    -1.04
     Future
    -0.93
    FUTURE
    -0.92
     futura
    -0.90
     FUTURE
    -0.88
     tomorrow
    -0.85
     CreateTagHelper
    -0.84
     propOrder
    -0.83
    POSITIVE LOGITS
    %">
    0.48
    //**
    0.47
    揭
    0.46
     çoğu
    0.45
    %;">
    0.43
    desc
    0.43
    .(*
    0.42
    //!
    0.42
    urnia
    0.41
     муніципалі
    0.41
    Activations Density 0.014%

    No Known Activations