© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-RES-MATRYOSHKA-DC
    7. 1473
    Prev
    Next
    INDEX
    Explanations

    transition words indicating contrast or consequence

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     pertanto
    -0.56
     accordingly
    -0.53
     perciò
    -0.48
    <bos>
    -0.47
     we
    -0.47
     definitivamente
    -0.47
     therefore
    -0.46
     consequently
    -0.45
     hence
    -0.45
     it
    -0.45
    POSITIVE LOGITS
     nahilalakip
    0.79
     nakalista
    0.79
     Wiktionnaire
    0.79
    ⓧ
    0.78
    
    0.77
     الدولى
    0.73
    umbersome
    0.69
     surla
    0.67
     EconPapers
    0.66
    RenderAtEndOf
    0.66
    Activations Density 0.501%

    No Known Activations