Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-RES-MATRYOSHKA-DC
    4. 46
    Prev
    Next
    INDEX
    Explanations

    mathematical and electrical sources related to modeling, specifically focusing on concepts like voltage, current, and their dependence in network systems

    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
     botanist
    -0.91
     hunne
    -0.90
     barbarous
    -0.90
     merciful
    -0.89
     astronomer
    -0.89
     astronomers
    -0.88
     histological
    -0.87
     copolymer
    -0.86
     Archaeological
    -0.84
     abominable
    -0.84
    POSITIVE LOGITS
     behavior
    0.96
     impact
    0.95
     activity
    0.95
     features
    0.94
     information
    0.92
     activities
    0.90
     content
    0.89
     resources
    0.89
     data
    0.82
     environment
    0.82
    Activations Density 20.336%

    No Known Activations