© 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. 10764
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and actions within a context

    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
    viewType
    -0.42
     lead
    -0.42
    نس
    -0.39
     led
    -0.38
    Lead
    -0.38
     별
    -0.38
     mène
    -0.37
     témoin
    -0.36
    Printable
    -0.36
     del
    -0.36
    POSITIVE LOGITS
     Мексичка
    0.96
    NameInMap
    0.91
     Италијани
    0.84
     мәкал
    0.83
    Datuak
    0.82
    IVEREF
    0.78
    addCriterion
    0.78
    WriteBarrier
    0.77
     propOrder
    0.76
    richTextPanel
    0.73
    Activations Density 0.485%

    No Known Activations