© 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. 14861
    Prev
    Next
    INDEX
    Explanations

    key terms related to primary sources and significant components in various contexts

    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
    exitRule
    -0.63
    valuable
    -0.56
    styleType
    -0.54
     CreateTagHelper
    -0.53
    ❮
    -0.52
     proud
    -0.51
    enumi
    -0.51
    ways
    -0.50
    repositories
    -0.50
     valuable
    -0.49
    POSITIVE LOGITS
    новниш
    0.64
    OGND
    0.62
     tuong
    0.61
     Gazetteer
    0.58
    러나
    0.57
    Izvori
    0.56
    الحياه
    0.56
     Gemü
    0.55
    évaluateur
    0.54
     بيها
    0.54
    Activations Density 0.099%

    No Known Activations