© 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. 5-CLT-HP
    7. 98177
    Prev
    Next
    INDEX
    Explanations

    on

    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
    Personendaten
    -1.05
     ModelExpression
    -1.01
    WithIOException
    -0.92
     <=",
    -0.91
     חיצוניים
    -0.91
    出版年
    -0.90
    Portail
    -0.89
     insuffisamment
    -0.89
    PerformLayout
    -0.86
    AddTagHelper
    -0.86
    POSITIVE LOGITS
     a
    0.73
     an
    0.51
     quicks
    0.44
     rapids
    0.43
    exif
    0.41
     World
    0.40
    ArrayOf
    0.40
     хорошего
    0.40
     seorang
    0.38
     έναν
    0.38
    Activations Density 0.001%

    No Known Activations