© 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. 4-CLT-HP
    7. 1384
    Prev
    Next
    INDEX
    Explanations

    news documents

    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
    NUMX
    -0.83
    verwijspagina
    -0.82
    RenderAtEndOf
    -0.79
    PerformLayout
    -0.78
    ModelAdmin
    -0.73
     SqlCommand
    -0.71
     שוליים
    -0.70
     незавершена
    -0.69
    ientôt
    -0.68
    IUrlHelper
    -0.67
    POSITIVE LOGITS
     to
    0.58
     of
    0.49
     í
    0.42
    Sorry
    0.42
     en
    0.42
    ,
    0.41
    мб
    0.41
    ↵↵
    0.41
     متعلقه
    0.41
    Ne
    0.40
    Activations Density 0.001%

    No Known Activations