© 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. 29149
    Prev
    Next
    INDEX
    Explanations

    the word "so" and its variations within the text

    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
    RetentionPolicy
    -0.76
     Dapper
    -0.76
     Uts
    -0.75
     EconPapers
    -0.71
     Trit
    -0.69
     triton
    -0.69
     kiệm
    -0.69
    NameInMap
    -0.68
     sockaddr
    -0.68
     Ples
    -0.68
    POSITIVE LOGITS
     sexu
    0.60
     Deane
    0.59
    Ещё
    0.58
    archiviato
    0.55
     boxes
    0.54
     vela
    0.53
     forth
    0.52
    ıyors
    0.52
     Latein
    0.52
     Aragón
    0.52
    Activations Density 0.009%

    No Known Activations