© 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. 5-CLT-HP
    7. 4305
    Prev
    Next
    INDEX
    Explanations

    Americans

    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
    expandindo
    -0.69
    Хьажоргаш
    -0.67
    AfterClass
    -0.62
    contentLoaded
    -0.60
    ArrowToggle
    -0.56
    例句
    -0.55
    atchewan
    -0.54
    ̎
    -0.54
     surla
    -0.54
    henswürdigkeiten
    -0.54
    POSITIVE LOGITS
    ंदीखरीदारी
    0.53
     Rami
    0.52
     CreateTagHelper
    0.49
     themselves
    0.49
     vay
    0.48
    ICom
    0.48
    Om
    0.47
     quæ
    0.46
    zzino
    0.45
     ſhe
    0.45
    Activations Density 0.003%

    No Known Activations