© 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. 13900
    Prev
    Next
    INDEX
    Explanations

    confusion

    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
     Confused
    -1.07
     confuse
    -1.01
     confuses
    -0.99
     confused
    -0.99
    Confused
    -0.95
    confused
    -0.85
     confound
    -0.83
     confounded
    -0.79
     confund
    -0.75
     bewildered
    -0.66
    POSITIVE LOGITS
    Personendaten
    0.68
    ActionMode
    0.64
    تقاوى
    0.61
    AddTagHelper
    0.60
     EconPapers
    0.60
    ingly
    0.55
     sprawie
    0.52
     Normdatei
    0.51
     عالية
    0.50
     typelib
    0.49
    Activations Density 0.005%

    No Known Activations