© 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. 3-RES-MATRYOSHKA-DC
    7. 1003
    Prev
    Next
    INDEX
    Explanations

    words relating to diseases, law, quantum computing, government positions, places and people's names

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Maren
    -1.02
     Persi
    -1.00
     Drog
    -0.99
     ARS
    -0.93
     setuptools
    -0.93
    IBOutlet
    -0.92
     Jeremiah
    -0.91
     Mourinho
    -0.90
     Henley
    -0.90
    WriteBarrier
    -0.89
    POSITIVE LOGITS
     Wilson
    0.85
     Steiner
    0.72
     McKinney
    0.70
     Dean
    0.69
     Yar
    0.68
    Yar
    0.67
     yar
    0.66
     WILSON
    0.66
     Dooley
    0.65
     Schroeder
    0.63
    Activations Density 4.528%

    No Known Activations