© 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. 12-RES-MATRYOSHKA-DC
    7. 32341
    Prev
    Next
    INDEX
    Explanations

    the transition words or phrases that indicate contrast or opposition 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
    Negative Logits
     autorytatywna
    -1.19
    fjspx
    -0.96
    MLLoader
    -0.94
     gynhyrchwyd
    -0.93
     مرئيه
    -0.91
    protoimpl
    -0.89
    MessageOf
    -0.89
    LookAnd
    -0.87
    الحياه
    -0.86
    principalColumn
    -0.85
    POSITIVE LOGITS
    norr
    0.51
     leiden
    0.50
     Hartmann
    0.49
    在我的
    0.47
    iro
    0.46
     interference
    0.45
     cómics
    0.44
     Neto
    0.43
    fato
    0.42
    が高い
    0.41
    Activations Density 0.039%

    No Known Activations