© 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. 30700
    Prev
    Next
    INDEX
    Explanations

    the presence of the acronym "BS" in various contexts

    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
    WriteLiteral
    -0.90
    الإنجليزية
    -0.74
    TemporalType
    -0.71
    Ij
    -0.69
     Nederland
    -0.68
    Hozzáférés
    -0.68
    исленность
    -0.68
     león
    -0.67
    //"
    -0.66
     diabe
    -0.65
    POSITIVE LOGITS
     BS
    1.34
    BS
    1.09
     bs
    1.06
    ")));
    1.05
    bs
    1.03
     photolibrary
    1.00
     itſelf
    0.91
     Jefus
    0.89
    $.
    0.88
     myſelf
    0.88
    Activations Density 0.011%

    No Known Activations