© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45632
    Prev
    Next
    INDEX
    Explanations

    overload/weary

    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
     referenties
    -0.78
     '\\;'
    -0.77
    setVerticalGroup
    -0.74
     overkill
    -0.71
     overflow
    -0.70
     oversize
    -0.69
     overload
    -0.69
     overloaded
    -0.68
     overworked
    -0.68
     outnumbered
    -0.68
    POSITIVE LOGITS
    ly
    0.58
    est
    0.51
    or
    0.46
    dish
    0.44
    RegressionTest
    0.44
    ord
    0.43
    ing
    0.43
    by
    0.42
    how
    0.42
    t
    0.41
    Activations Density 0.969%

    No Known Activations