© 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. 20-CLT-HP
    7. 71617
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Task
    -0.86
     task
    -0.82
    Task
    -0.81
     Assignment
    -0.78
     TASK
    -0.75
     ASSIGNMENT
    -0.73
    task
    -0.71
     Aufgabe
    -0.69
     assignment
    -0.68
    tagHelperRunner
    -0.65
    POSITIVE LOGITS
     kiin
    0.59
    XmlAccessType
    0.57
     fær
    0.55
    Tē
    0.55
     تضيفلها
    0.55
     leçons
    0.54
     længere
    0.53
     mukaan
    0.52
     unités
    0.51
    GEBURTSDATUM
    0.51
    Activations Density 0.000%

    No Known Activations