© 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. 23340
    Prev
    Next
    INDEX
    Explanations

    expressions of personal fulfillment and self-improvement

    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
    ioutil
    -0.73
     Suggest
    -0.57
    Referências
    -0.53
     تانيه
    -0.49
     SUGGEST
    -0.49
    odb
    -0.48
    âmica
    -0.48
     suger
    -0.48
    লি
    -0.47
    OLPH
    -0.47
    POSITIVE LOGITS
    RectangleBorder
    0.73
    liflower
    0.65
     propOrder
    0.64
    )':
    0.62
    AddTagHelper
    0.61
     iconTwitter
    0.60
    ArrowToggle
    0.59
     coaching
    0.58
     coached
    0.58
    Хьажоргаш
    0.57
    Activations Density 0.093%

    No Known Activations