© 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. 77635
    Prev
    Next
    INDEX
    Explanations

    Code snippets/unusual text

    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
     autorytatywna
    -0.73
    atguigu
    -0.67
     typelib
    -0.64
    +#+#
    -0.61
    tagHelperRunner
    -0.61
    Autoritní
    -0.56
    DockStyle
    -0.54
    forChild
    -0.53
    rrggbb
    -0.53
    Démographie
    -0.53
    POSITIVE LOGITS
    achite
    0.57
    %',
    0.56
     '{@
    0.52
    Newswire
    0.50
    meen
    0.50
    $")
    0.49
    %")
    0.48
    moveToFirst
    0.47
    esModule
    0.47
     propre
    0.46
    Activations Density 0.003%

    No Known Activations