© 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. 20094
    Prev
    Next
    INDEX
    Explanations

    references to particular individuals and their relationships to each other in a narrative context

    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
    Not in Any Lists

    No Comments

    Negative Logits
    vore
    -0.48
     useHistory
    -0.46
    timewa
    -0.46
    ক্ত
    -0.45
     Respon
    -0.45
    Istorija
    -0.45
     fallacy
    -0.44
    luo
    -0.44
     respon
    -0.43
     thiếu
    -0.43
    POSITIVE LOGITS
     neighbor
    0.77
     neighbors
    0.77
     neigh
    0.75
    MemoryWarning
    0.74
     neighbours
    0.73
    neighbor
    0.73
     neighbour
    0.73
    Portail
    0.70
     roommate
    0.69
     NEIGH
    0.69
    Activations Density 0.173%

    No Known Activations