© 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. 23109
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or intention

    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
    Hauptartikel
    -0.62
    الإنجليزية
    -0.61
    RegistryLite
    -0.59
     المتحدة
    -0.55
    abestanden
    -0.52
    Diweddarwch
    -0.51
    BarButtonItem
    -0.50
    授
    -0.50
    }){
    -0.50
    AsUp
    -0.48
    POSITIVE LOGITS
    PerformLayout
    0.66
    anskje
    0.60
    łyn
    0.59
    Pyx
    0.59
     altes
    0.59
    calaure
    0.58
     BIBSYS
    0.58
     bulunabilir
    0.58
    cloud
    0.57
     JUGA
    0.57
    Activations Density 0.005%

    No Known Activations