© 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. 20-CLT-HP
    7. 74813
    Prev
    Next
    INDEX
    Explanations

    Code/technical documents

    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
    MLLoader
    -0.58
     XCTest
    -0.50
    InjectAttribute
    -0.47
     Añ
    -0.45
    fac
    -0.45
    Datuak
    -0.44
     Pase
    -0.44
     ویکی‌پدیا
    -0.44
     szem
    -0.43
    écoute
    -0.43
    POSITIVE LOGITS
    ngdoc
    0.73
    /**
    0.68
    #!/
    0.63
     للمعارف
    0.61
    monary
    0.54
     financeiro
    0.54
     consultato
    0.54
    </tfoot>
    0.51
     estimés
    0.51
    NameInMap
    0.51
    Activations Density 0.000%

    No Known Activations