© 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. 25347
    Prev
    Next
    INDEX
    Explanations

    references to a specific subject or entity, particularly the word "the."

    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
    addCriterion
    -0.78
    ymce
    -0.74
    ftagPool
    -0.70
    Namara
    -0.68
    клопе
    -0.68
    uxxxx
    -0.67
    adaptiveStyles
    -0.66
     PyLong
    -0.66
    ureau
    -0.65
     Whitaker
    -0.64
    POSITIVE LOGITS
    GMENT
    0.59
    anganronpa
    0.55
    Said
    0.54
    findpost
    0.54
    Биография
    0.52
     obstante
    0.52
    例句
    0.52
     myſelf
    0.50
     Gout
    0.50
     mariner
    0.50
    Activations Density 0.028%

    No Known Activations