© 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. 0-CLT-HP
    7. 94676
    Prev
    Next
    INDEX
    Explanations

    complex

    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
     complex
    -2.97
    complex
    -2.50
    Complex
    -2.30
     Complex
    -2.28
     COMPLEX
    -1.98
     complexe
    -1.92
     complicated
    -1.91
     komplex
    -1.84
     complexity
    -1.83
     complexo
    -1.78
    POSITIVE LOGITS
     heapq
    0.71
    Hentet
    0.65
    DIPSETTING
    0.63
     monoch
    0.63
     diak
    0.62
     epithelium
    0.59
     stoneware
    0.59
    izing
    0.57
    posedge
    0.57
    pylene
    0.56
    Activations Density 0.392%

    No Known Activations