© 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. 73152
    Prev
    Next
    INDEX
    Explanations

    center

    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
     onCreateView
    -0.87
     nonUne
    -0.81
    ⓧ
    -0.79
    InitVars
    -0.78
     disambiguazione
    -0.77
    Aholisi
    -0.77
    queryInterface
    -0.75
     typelib
    -0.74
     initComponents
    -0.73
    ssysteme
    -0.73
    POSITIVE LOGITS
     center
    0.56
     m
    0.54
    M
    0.48
     M
    0.47
     centers
    0.46
    center
    0.43
     Center
    0.39
    m
    0.38
    モ
    0.38
     centre
    0.38
    Activations Density 0.001%

    No Known Activations