© 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. 31871
    Prev
    Next
    INDEX
    Explanations

    numeric values and numerical 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
     autorytatywna
    -0.88
    Datuak
    -0.87
    Personendaten
    -0.81
     kiệm
    -0.80
    ulemon
    -0.80
     Bethany
    -0.79
    CppCodeGen
    -0.77
    بوابة
    -0.77
    原始内容存档于
    -0.75
     bellows
    -0.75
    POSITIVE LOGITS
     incu
    0.60
    psack
    0.58
     Silverman
    0.57
     Ware
    0.56
    ILO
    0.55
    ilo
    0.54
     Ло
    0.54
     cun
    0.53
    ान
    0.53
    oudre
    0.53
    Activations Density 0.120%

    No Known Activations