© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72354
    Prev
    Next
    INDEX
    Explanations

    get

    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
    exitRule
    -0.69
    addCriterion
    -0.67
    IsMutable
    -0.65
     getItemId
    -0.60
     enfans
    -0.60
    Capítulo
    -0.59
    urlpatterns
    -0.57
     passés
    -0.57
     Greater
    -0.57
    uncher
    -0.57
    POSITIVE LOGITS
    TagMode
    0.59
    BeginContext
    0.55
    }();
    0.51
     متعلقه
    0.50
    ViewImports
    0.47
     Roskov
    0.46
     AspNetCore
    0.46
     Normdatei
    0.45
    AddTagHelper
    0.45
    rungsseite
    0.44
    Activations Density 0.001%

    No Known Activations