© 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. 95576
    Prev
    Next
    INDEX
    Explanations

    department

    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
     Department
    -0.79
     department
    -0.68
    Department
    -0.60
    StreetMap
    -0.58
     DEPARTMENT
    -0.56
     Dept
    -0.54
     consultation
    -0.54
     maintenance
    -0.53
     profession
    -0.51
     departments
    -0.51
    POSITIVE LOGITS
    yarnpkg
    0.63
     of
    0.63
     tarko
    0.61
     EdgeInsets
    0.60
     BoxDecoration
    0.59
    CloseOperation
    0.58
    StoryboardSegue
    0.57
    !*\
    0.57
    WriteTagHelper
    0.56
     [*]
    0.56
    Activations Density 0.020%

    No Known Activations