© 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. 91084
    Prev
    Next
    INDEX
    Explanations

    are

    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
    Geplaatst
    -0.70
    /*
    -0.58
    IContainer
    -0.58
     hâte
    -0.56
     fidèles
    -0.55
     soñ
    -0.55
     &___
    -0.54
     rêves
    -0.54
     "..\..\
    -0.53
     élas
    -0.53
    POSITIVE LOGITS
    makeConstraints
    0.65
     instead
    0.58
    AccessorTable
    0.57
    Obrázky
    0.57
     ddelweddau
    0.52
     did
    0.51
    حياتها
    0.50
    حياته
    0.47
    Hentet
    0.47
     DbSet
    0.47
    Activations Density 0.013%

    No Known Activations