© 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. 20446
    Prev
    Next
    INDEX
    Explanations

    references to sports achievements and conference records

    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
     Efq
    -1.25
     Jefus
    -1.15
     myſelf
    -1.15
     houſe
    -1.13
     itſelf
    -1.13
     Monfieur
    -1.10
    تقاوى
    -1.09
     Majefty
    -1.09
     pleaſure
    -1.09
     himſelf
    -1.07
    POSITIVE LOGITS
     co
    0.56
     c
    0.55
    転
    0.55
    conf
    0.52
     Sch
    0.51
    ex
    0.50
    ighton
    0.50
     to
    0.50
    Ậ
    0.49
     Ag
    0.48
    Activations Density 0.006%

    No Known Activations