© 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. 1-CLT-HP
    7. 13600
    Prev
    Next
    INDEX
    Explanations

    umes

    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
    umes
    -1.52
    ume
    -1.48
    UME
    -1.27
    UMES
    -0.84
    umed
    -0.81
    umi
    -0.77
    uming
    -0.64
    uma
    -0.57
    umer
    -0.54
    umé
    -0.52
    POSITIVE LOGITS
     nahilalakip
    0.83
    expandindo
    0.67
     المعيارى
    0.66
     Ophelia
    0.65
    таратура
    0.63
    ReusableCell
    0.61
    ]})
    0.60
     eventdata
    0.60
     QWidget
    0.60
    endregion
    0.59
    Activations Density 0.025%

    No Known Activations