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. 12-RES-MATRYOSHKA-DC
    4. 87
    Prev
    Next
    INDEX
    Explanations

    connections between cause and effect in statements

    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
     hierogly
    -0.95
     Cæsar
    -0.94
     Efq
    -0.78
     Pelop
    -0.77
     Shakspeare
    -0.77
     Esau
    -0.77
     Sopho
    -0.75
     Shaksp
    -0.75
     Teut
    -0.73
     moschino
    -0.73
    POSITIVE LOGITS
     it
    1.30
     the
    1.24
     we
    1.09
     they
    1.08
    )";
    
    1.04
     there
    1.02
    "):
    
    1.02
    )");
    
    0.98
     when
    0.96
     these
    0.95
    Activations Density 4.871%

    No Known Activations