© 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. 6236
    Prev
    Next
    INDEX
    Explanations

    "to be" verb

    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
    Démographie
    -0.64
    ScopeManager
    -0.61
     himo
    -0.54
    StreetMap
    -0.53
    NamedQueries
    -0.53
    BorderFactory
    -0.52
     gynhyrchwyd
    -0.52
     endwhile
    -0.52
    setVerticalGroup
    -0.51
     CommandType
    -0.50
    POSITIVE LOGITS
     my
    0.57
     Hauser
    0.52
     a
    0.52
     intermédiaire
    0.49
    الإنجليزية
    0.49
    нгредіє
    0.47
     BioLib
    0.47
     an
    0.46
     useRef
    0.46
    Referencie
    0.45
    Activations Density 0.001%

    No Known Activations