© 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. 91065
    Prev
    Next
    INDEX
    Explanations

    programming/coding subclasses/inheritance

    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
    cipar
    -0.49
     تانيه
    -0.49
     son
    -0.48
    filepath
    -0.47
     leaning
    -0.46
    UserScript
    -0.46
     Shir
    -0.46
     parenting
    -0.46
     lighthouse
    -0.45
    ONOMY
    -0.45
    POSITIVE LOGITS
    IMPORTED
    0.68
    EndContext
    0.67
    FieldNumber
    0.60
     JpaRepository
    0.59
    hoeddwyd
    0.58
    ensement
    0.57
    LayoutStyle
    0.52
     Collection
    0.52
     Mutable
    0.52
    Personensuche
    0.51
    Activations Density 0.006%

    No Known Activations