© 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. 21241
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "taken together" or summarizing collective findings

    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
     Parcelable
    -0.70
    setViewName
    -0.68
     ardor
    -0.60
    ії
    -0.60
    portes
    -0.57
    epam
    -0.57
    готовление
    -0.57
     antaranya
    -0.57
     Riggs
    -0.57
    t
    -0.57
    POSITIVE LOGITS
    eken
    0.93
    gatsby
    0.90
    LookAnd
    0.89
     للاسماء
    0.86
    Drawn
    0.83
    /*
    0.82
    jsonwebtoken
    0.82
     flown
    0.81
     Kuan
    0.81
    >`
    0.80
    Activations Density 0.030%

    No Known Activations