© 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. 14941
    Prev
    Next
    INDEX
    Explanations

    events related to sports and competition

    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
     TextAppearance
    -0.52
    śród
    -0.47
    CommandType
    -0.46
    urie
    -0.45
    veloppement
    -0.44
    putable
    -0.44
     viata
    -0.44
     însă
    -0.44
    రి
    -0.43
    STA
    -0.43
    POSITIVE LOGITS
     repeatedly
    0.89
     twice
    0.81
     frequently
    0.78
    expandindo
    0.75
     &___
    0.74
     every
    0.74
    frequently
    0.71
     repeated
    0.69
     Repeated
    0.69
     frequ
    0.68
    Activations Density 0.347%

    No Known Activations