© 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. 5-CLT-HP
    7. 4488
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     doors
    -0.53
    AlterField
    -0.52
    endpush
    -0.51
     akong
    -0.50
    libft
    -0.50
     gills
    -0.50
    ولايات
    -0.49
     Macbeth
    -0.48
    popd
    -0.48
    zeba
    -0.47
    POSITIVE LOGITS
    ⓧ
    0.72
    脚注の使い方
    0.66
    RegressionTest
    0.65
    TestingModule
    0.64
     nahilalakip
    0.60
    CppMethod
    0.59
    MENAFN
    0.58
    Hentet
    0.58
    Referanser
    0.57
    TagMode
    0.55
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.