© 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. 1-CLT-HP
    7. 15261
    Prev
    Next
    INDEX
    Explanations

    government

    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
    AndEndTag
    -0.86
     newBuilder
    -0.64
    fromnode
    -0.59
     autorytatywna
    -0.54
    StructEnd
    -0.53
    aarrggbb
    -0.52
    出版年
    -0.52
     stället
    -0.52
    :✨
    -0.52
     BoxFit
    -0.50
    POSITIVE LOGITS
     U
    0.59
     fusca
    0.56
     <>",
    0.55
     AssemblyTitle
    0.53
    antd
    0.52
     voids
    0.50
     Insee
    0.50
     pymysql
    0.49
    angkan
    0.49
     Exist
    0.49
    Activations Density 0.020%

    No Known Activations