© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43476
    Prev
    Next
    INDEX
    Explanations

    required

    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
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.59
     Efq
    -0.59
     esternos
    -0.57
     respectivement
    -0.54
    OrBuilder
    -0.54
     useStyles
    -0.53
    AntiForgeryToken
    -0.52
     désolés
    -0.52
    antaranya
    -0.51
     EconPapers
    -0.51
    POSITIVE LOGITS
    Rüyada
    0.62
    Демографія
    0.59
    ScopeManager
    0.57
    GHIJKLM
    0.56
     للاسماء
    0.53
    enment
    0.51
     cara
    0.50
    pshots
    0.50
     autorytatywna
    0.50
    veur
    0.50
    Activations Density 0.048%

    No Known Activations