© 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. 23545
    Prev
    Next
    INDEX
    Explanations

    words that express agreement or connection between ideas in a discussion or argument

    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
    urante
    -0.64
    oxys
    -0.63
     theo
    -0.59
    ArrowToggle
    -0.59
     configureStore
    -0.58
    Rüyada
    -0.56
     Denn
    -0.55
    YON
    -0.55
    shmi
    -0.55
     TableColumn
    -0.54
    POSITIVE LOGITS
     bahwa
    0.71
     Normdatei
    0.66
    stateProvider
    0.62
     that
    0.60
     חיצוניים
    0.59
     iemand
    0.57
     lèvres
    0.55
    󠁴
    0.53
     oreilles
    0.52
     inwardly
    0.52
    Activations Density 0.167%

    No Known Activations