© 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. 6318
    Prev
    Next
    INDEX
    Explanations

    apostrophe

    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
    tagHelperRunner
    -0.75
     EconPapers
    -0.62
    évaluateur
    -0.62
    Autoritní
    -0.60
    Personensuche
    -0.57
    ########.
    -0.57
     وتسجيلات
    -0.57
     autorytatywna
    -0.56
    agaimana
    -0.56
    toBeTruthy
    -0.55
    POSITIVE LOGITS
    ViewById
    0.51
    StoryboardSegue
    0.49
    BufferException
    0.45
    rientes
    0.45
     архивлан
    0.45
    engertian
    0.44
     useState
    0.44
     veci
    0.42
    abyte
    0.42
    medad
    0.42
    Activations Density 0.006%

    No Known Activations