© 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. 25317
    Prev
    Next
    INDEX
    Explanations

    key responses and confirmations in a question-and-answer format

    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
    ArgumentParser
    -0.60
    VersionUID
    -0.56
    WebVitals
    -0.56
    IonicModule
    -0.56
     Vikipedi
    -0.53
    )</
    -0.52
     ID
    -0.52
    ulco
    -0.52
    Editora
    -0.51
     hearts
    -0.51
    POSITIVE LOGITS
    gæ
    0.56
    ounced
    0.53
    FECTION
    0.52
     conç
    0.50
    findpost
    0.48
     appuntamento
    0.47
     Numerade
    0.47
    Yeet
    0.47
     découver
    0.47
    varande
    0.47
    Activations Density 0.006%

    No Known Activations