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. 85
    Prev
    Next
    INDEX
    Explanations

    conjunctions and alternatives in sentence structures

    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
     tric
    -0.68
     Shakspeare
    -0.68
     Weyl
    -0.65
     Independiente
    -0.63
     ")");
    -0.62
    )");
    
    -0.61
     cocco
    -0.61
     Hauptmann
    -0.61
    yczą
    -0.60
     nemlig
    -0.60
    POSITIVE LOGITS
     or
    1.53
     atau
    1.30
     یا
    1.29
     Or
    1.28
     oder
    1.25
     otherwise
    1.24
     eller
    1.24
     OR
    1.21
    หรือ
    1.20
     vagy
    1.20
    Activations Density 0.718%

    No Known Activations