© 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. 15306
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitional words that contrast or introduce an exception

    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
     InputDecoration
    -1.02
    ftagPool
    -0.96
     nakalista
    -0.91
    CppCodeGen
    -0.90
    ViewFeatures
    -0.90
    帖最后由
    -0.80
    expandindo
    -0.79
    UnsafeEnabled
    -0.79
     JpaRepository
    -0.77
     Roskov
    -0.77
    POSITIVE LOGITS
     But
    0.63
    But
    0.61
     Butler
    0.54
    confirmButton
    0.52
    ut
    0.52
    but
    0.51
     BUTLER
    0.49
    もありますが
    0.48
    di
    0.47
    "${
    0.45
    Activations Density 0.026%

    No Known Activations