© 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. 32623
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships and associations

    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
     Мексичка
    -0.79
    脚注の使い方
    -0.73
    Tikang
    -0.69
    tagHelperRunner
    -0.66
    رشف
    -0.65
     invokingState
    -0.63
    Vidite
    -0.61
     '\\;'
    -0.61
     ovp
    -0.60
     theſe
    -0.59
    POSITIVE LOGITS
    例文帳に追加
    0.53
     choice
    0.51
     оригіналу
    0.49
    inai
    0.49
     bất
    0.48
    piri
    0.46
    Indented
    0.46
     geworden
    0.45
     ảo
    0.45
     partout
    0.45
    Activations Density 0.149%

    No Known Activations