© 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. 5979
    Prev
    Next
    INDEX
    Explanations

    phrases related to subjects and conditions that impose limitations or constraints

    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
     مشين
    -0.71
    LogFactory
    -0.70
     myſelf
    -0.69
     sanity
    -0.64
     thyself
    -0.63
     disponibilités
    -0.62
    UnifiedTopology
    -0.60
     Efq
    -0.59
    jmniej
    -0.59
     Eſ
    -0.56
    POSITIVE LOGITS
     undergoes
    0.85
     undergo
    0.84
    受
    0.78
     undergoing
    0.77
     suffer
    0.73
     AssemblyCulture
    0.72
     underwent
    0.71
     sofrer
    0.71
     suffers
    0.69
     sufrir
    0.68
    Activations Density 0.330%

    No Known Activations