© 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. 32585
    Prev
    Next
    INDEX
    Explanations

    references to locations, people, or organizations

    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
    umumkan
    -0.78
     Reuben
    -0.51
     cuadrado
    -0.51
    bieten
    -0.49
     humaine
    -0.49
     Católica
    -0.49
     råd
    -0.48
     télécharge
    -0.48
     locust
    -0.48
    ệu
    -0.48
    POSITIVE LOGITS
     propOrder
    0.63
     дописавши
    0.60
    بوابة
    0.60
    XmlAccessType
    0.60
     kasarigan
    0.56
    SaveChangesAsync
    0.54
    ospel
    0.50
    rungsseite
    0.50
    endwhile
    0.50
     consultato
    0.50
    Activations Density 0.661%

    No Known Activations