© 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. 27118
    Prev
    Next
    INDEX
    Explanations

    technical fields or categories related to inventions

    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
     role
    -0.54
    adaptiveStyles
    -0.54
    medriver
    -0.51
    findpost
    -0.50
    jelent
    -0.48
     roles
    -0.46
    ijnt
    -0.46
    databind
    -0.45
    IMIENTO
    -0.45
    Télé
    -0.45
    POSITIVE LOGITS
    sidemargin
    0.75
    CharStream
    0.67
     excès
    0.66
     незавершена
    0.62
    Diweddarwch
    0.62
    Geplaatst
    0.61
     estekak
    0.59
     disambiguazione
    0.58
     EconPapers
    0.57
    ільки
    0.56
    Activations Density 0.009%

    No Known Activations