© 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. 15402
    Prev
    Next
    INDEX
    Explanations

    esq

    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
     subsp
    -1.16
     Esq
    -0.64
     specchio
    -0.62
     enfans
    -0.61
    ibility
    -0.58
     étend
    -0.58
    Спољашње
    -0.57
     angef
    -0.56
     igång
    -0.56
    ちょうど
    -0.55
    POSITIVE LOGITS
     propOrder
    0.70
     nahilalakip
    0.68
    LabelTagHelper
    0.54
    soka
    0.53
     ویکی‌آمباردا
    0.51
    RenderAtEndOf
    0.51
     اطلع
    0.49
    CDCl
    0.49
     <=",
    0.49
    onomía
    0.48
    Activations Density 0.006%

    No Known Activations