© 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. 1-CLT-HP
    7. 13780
    Prev
    Next
    INDEX
    Explanations

    demographic studies/place names

    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
     estekak
    -0.62
     Huma
    -0.57
     resourceCulture
    -0.56
    vitt
    -0.56
    </tfoot>
    -0.55
    IsPostBack
    -0.54
     Ame
    -0.52
     viewWillAppear
    -0.52
    ietic
    -0.50
    TestClass
    -0.49
    POSITIVE LOGITS
    InjectAttribute
    0.58
    GEBURTS
    0.56
    PreferredItem
    0.54
     Meksiku
    0.54
    findpost
    0.54
    ///</
    0.53
    पया
    0.52
     nevo
    0.50
    فایل‌لار
    0.50
    ScopeManager
    0.49
    Activations Density 0.009%

    No Known Activations