© 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. 95657
    Prev
    Next
    INDEX
    Explanations

    overflow

    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
     Satellite
    -0.69
    ing
    -0.64
    Satellite
    -0.64
    lemek
    -0.61
    abestanden
    -0.59
    satellite
    -0.55
    ING
    -0.52
    المناصب
    -0.52
    GenerationType
    -0.51
     CreateTagHelper
    -0.50
    POSITIVE LOGITS
    ImageContext
    0.71
     OWL
    0.59
    /*
    0.59
    قایناق‌لار
    0.57
    Всем
    0.54
    NameInMap
    0.54
     tric
    0.53
     tdci
    0.53
     PHI
    0.52
     unden
    0.52
    Activations Density 0.302%

    No Known Activations