© 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. 9222
    Prev
    Next
    INDEX
    Explanations

    phrases expressing capability or ability to take action

    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
     mắn
    -0.67
     gracilis
    -0.67
     attempt
    -0.63
    tagHelper
    -0.61
     tentativa
    -0.61
     craindre
    -0.60
     tentativo
    -0.60
     manto
    -0.59
     vermogen
    -0.59
     Dodson
    -0.58
    POSITIVE LOGITS
    crollView
    0.80
    存于互联网档案馆
    0.79
     Audiodateien
    0.79
     simplifié
    0.78
    دانشنامهٔ
    0.76
    Portail
    0.76
    Бахар
    0.74
    ReusableCell
    0.72
     "];
    0.71
    CloseOperation
    0.70
    Activations Density 0.006%

    No Known Activations