© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15937
    Prev
    Next
    INDEX
    Explanations

    instances of the action of purchasing or buying

    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
     purchased
    -0.96
     acquired
    -0.89
     Purchased
    -0.85
     Acquired
    -0.82
     متعلقه
    -0.81
    Autoritní
    -0.81
    acquired
    -0.80
    Acquired
    -0.80
     acquisition
    -0.79
    Acquisition
    -0.79
    POSITIVE LOGITS
     buying
    2.19
     Buying
    2.02
    buying
    1.95
    Buying
    1.83
     purchasing
    1.13
     Purchasing
    0.99
     buyers
    0.91
     ordering
    0.89
     buyer
    0.88
     Buyer
    0.86
    Activations Density 0.004%

    No Known Activations