© 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. 25319
    Prev
    Next
    INDEX
    Explanations

    specific conjunctions and phrases that emphasize conditional relationships

    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
     likewise
    -0.55
    ագրություններ
    -0.54
     similarly
    -0.51
    GOTREF
    -0.51
     idem
    -0.47
    同じく
    -0.47
     Boyce
    -0.44
    학
    -0.44
    faker
    -0.43
    hely
    -0.43
    POSITIVE LOGITS
     mergeFrom
    0.91
    tagHelperRunner
    0.88
    SourceChecksum
    0.79
    awtextra
    0.77
    Geplaatst
    0.70
    sizeCache
    0.70
    Tē
    0.69
    SharedCtor
    0.69
    الإنجليزية
    0.68
    :✨
    0.68
    Activations Density 0.000%

    No Known Activations