© 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. 6009
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Moreover" and other similar transition phrases

    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
     BoxFit
    -0.76
     оригіналу
    -0.74
    WebVitals
    -0.74
    EndContext
    -0.67
    s
    -0.66
    contentLoaded
    -0.64
    ke
    -0.62
    SourceChecksum
    -0.60
     Hit
    -0.59
    RRect
    -0.59
    POSITIVE LOGITS
    theless
    0.84
    amını
    0.74
    bibfield
    0.73
    Đặc
    0.73
    vency
    0.70
    ecture
    0.68
     lär
    0.68
    &+
    0.68
    Добавлено
    0.68
     Theſe
    0.68
    Activations Density 0.019%

    No Known Activations