© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95681
    Prev
    Next
    INDEX
    Explanations

    technology

    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
    Negative Logits
     technology
    -1.31
    technology
    -1.28
    Technology
    -1.24
     TECHNOLOGY
    -1.20
     Technology
    -1.16
     nakalista
    -1.15
     tecnolog
    -1.14
     tecnología
    -1.14
    TECHNOLOGY
    -1.12
     Paglinawan
    -1.09
    POSITIVE LOGITS
     for
    0.70
    ,
    0.51
     “
    0.51
     now
    0.49
     (
    0.48
     with
    0.47
    .
    0.45
     T
    0.45
     f
    0.45
    -
    0.44
    Activations Density 0.172%

    No Known Activations