© 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. 31931
    Prev
    Next
    INDEX
    Explanations

    references to historical or archaeological sites

    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
    发表于
    -1.11
    ſelf
    -0.98
    ]")]
    -0.96
     AssemblyCulture
    -0.95
    ſelves
    -0.95
    بوابة
    -0.94
    вгений
    -0.93
     poffe
    -0.92
    saraba
    -0.91
     незавершена
    -0.90
    POSITIVE LOGITS
      
    0.63
     x
    0.60
     EVERY
    0.59
     blah
    0.57
     HUGE
    0.57
     we
    0.57
     VERY
    0.56
     t
    0.55
     pretty
    0.54
     ENTIRE
    0.54
    Activations Density 0.520%

    No Known Activations