© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 40525
    Prev
    Next
    INDEX
    Explanations

    export

    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
     export
    -1.27
     import
    -1.27
     Export
    -1.07
     exported
    -1.06
     exporting
    -1.01
    import
    -0.94
     Import
    -0.91
     EXPORT
    -0.91
     exports
    -0.89
     exportation
    -0.89
    POSITIVE LOGITS
    BeginContext
    0.58
     autorytatywna
    0.51
     jspb
    0.46
    multer
    0.45
    ::_('
    0.44
     économiques
    0.44
    bido
    0.44
    InjectAttribute
    0.44
    CodedInputStream
    0.43
    ("/:
    0.42
    Activations Density 0.050%

    No Known Activations