© 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. 18848
    Prev
    Next
    INDEX
    Explanations

    conjunctions that introduce contrast or 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
    Negative Logits
     jotka
    -0.57
    NameInMap
    -0.57
     hanem
    -0.55
    ządu
    -0.54
    sino
    -0.53
    ))->
    -0.52
    __]
    -0.52
     autorytatywna
    -0.52
    ="@+
    -0.52
    thoff
    -0.51
    POSITIVE LOGITS
    principalTable
    0.76
    findpost
    0.67
    دانشنامهٔ
    0.66
    AntiForgeryToken
    0.57
    esez
    0.56
     potr
    0.55
     getItemCount
    0.55
     krop
    0.55
     bushel
    0.54
    MessageTagHelper
    0.54
    Activations Density 0.074%

    No Known Activations