© 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. 5-CLT-HP
    7. 90992
    Prev
    Next
    INDEX
    Explanations

    speaking

    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
     laikā
    -0.54
    guidance
    -0.51
     económicas
    -0.50
     leçons
    -0.49
    Guidance
    -0.49
     desvan
    -0.47
     väg
    -0.47
     débats
    -0.47
     trucos
    -0.47
     fortement
    -0.47
    POSITIVE LOGITS
    enumi
    0.97
     numerus
    0.59
     Wikispecies
    0.58
     jsPsych
    0.58
    awtextra
    0.57
     cref
    0.57
    Personensuche
    0.56
    
    0.53
     ſeveral
    0.53
     chain
    0.53
    Activations Density 0.005%

    No Known Activations