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. 32
    Prev
    Next
    INDEX
    Explanations

    terms related to standards and regulatory specifications in various contexts

    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
     geologists
    -0.83
     condoms
    -0.80
     suivie
    -0.78
     officiellement
    -0.78
     anthropologists
    -0.78
     auxquelles
    -0.77
     démission
    -0.77
     beetles
    -0.76
     giudi
    -0.75
     dysplasia
    -0.75
    POSITIVE LOGITS
    neſs
    1.23
    )";
    
    1.20
     $_"
    1.16
    leſs
    1.15
    )");
    
    1.12
    eſt
    1.11
    ^(@)
    1.10
    %");
    1.06
    */;
    1.05
    .";
    
    1.05
    Activations Density 8.332%

    No Known Activations