© 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. 1-CLT-HP
    7. 8639
    Prev
    Next
    INDEX
    Explanations

    travel

    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
     linkovi
    -0.53
    Portale
    -0.52
    setVerticalGroup
    -0.52
    RunWith
    -0.50
    setViewName
    -0.47
    leche
    -0.46
    ContextHolder
    -0.45
    unj
    -0.44
    ViewFeatures
    -0.44
    Portail
    -0.43
    POSITIVE LOGITS
    LEncoder
    0.68
    WAH
    0.59
     BoxDecoration
    0.57
    zee
    0.56
    Пока
    0.55
     newName
    0.54
     <<<<<<<<<<<<<<
    0.53
    存于互联网档案馆
    0.53
    saurus
    0.52
    tzmann
    0.50
    Activations Density 0.014%

    No Known Activations