© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14147
    Prev
    Next
    INDEX
    Explanations

    Saudi

    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
     للاسماء
    -0.84
    ggior
    -0.76
    <!--[
    -0.70
    rawDesc
    -0.68
    (")");
    -0.68
     الدولى
    -0.68
     चीज़ों
    -0.68
    enderror
    -0.66
    SBATCH
    -0.66
    msgTypes
    -0.65
    POSITIVE LOGITS
     Mount
    0.42
    ็จ
    0.40
    igate
    0.38
    PRNewswire
    0.38
     Leib
    0.37
     Watson
    0.37
     cale
    0.36
    ITOR
    0.36
    ppu
    0.36
    SourceChecksum
    0.35
    Activations Density 0.030%

    No Known Activations