© 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-RES-MATRYOSHKA-DC
    7. 159
    Prev
    Next
    INDEX
    Explanations

    references to websites or online resources, specifically domain names or web addresses

    oai_token-act-pair · gpt-4.1-nano
    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
     comparison
    -0.84
    CodeAttribute
    -0.82
     myſelf
    -0.80
     comparative
    -0.79
    CompleteListener
    -0.79
     comparación
    -0.79
    Comparison
    -0.78
     comparação
    -0.77
    Comparative
    -0.76
    comparison
    -0.75
    POSITIVE LOGITS
    com
    3.30
    org
    2.03
     com
    1.94
    Com
    1.72
    COM
    1.69
    coms
    1.55
     Com
    1.44
     org
    1.29
    ORG
    1.21
    Org
    1.13
    Activations Density 0.975%

    No Known Activations