© 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. 72800
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    <?
    -0.61
     gọn
    -0.58
    growing
    -0.56
    RenderAtEndOf
    -0.55
    prepareStatement
    -0.54
     [*]
    -0.53
     Grosvenor
    -0.52
    ąż
    -0.51
    JpaRepository
    -0.50
    []>(
    -0.49
    POSITIVE LOGITS
    +#+#
    0.56
    Geplaatst
    0.55
     kasarigan
    0.53
     replaced
    0.52
    AsUp
    0.50
    ISupport
    0.49
    InputTagHelper
    0.49
    uxxxx
    0.48
    principalTable
    0.48
     infected
    0.46
    Activations Density 0.000%

    No Known Activations