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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 8604
    Prev
    Next
    INDEX
    Explanations

    scientific evidence and data related to medical research

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reports
    -0.52
    Unmarshaller
    -0.52
     report
    -0.50
     analysis
    -0.50
    ohistochemistry
    -0.49
     Reports
    -0.48
     surla
    -0.47
     image
    -0.47
     hist
    -0.47
    нан
    -0.46
    POSITIVE LOGITS
     purpoſe
    0.78
     pleaſure
    0.77
     ſtate
    0.76
     houſe
    0.72
     leçon
    0.70
     amitié
    0.70
     Jefus
    0.69
     reaſon
    0.69
     Monfieur
    0.69
     uſe
    0.68
    Activations Density 0.070%

    No Known Activations