© 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. 5956
    Prev
    Next
    INDEX
    Explanations

    instances of conjunctions and various types of food-related terms

    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
    TypedDataSet
    -0.73
    gdx
    -0.66
    )}</
    -0.65
    queryInterface
    -0.65
    }),
    -0.63
    tvguidetime
    -0.63
    %");
    -0.62
    ngrx
    -0.60
    )}
    -0.58
     arşivlendi
    -0.57
    POSITIVE LOGITS
    ">//
    0.56
     adulta
    0.53
     تضيفلها
    0.52
    IUrlHelper
    0.51
    otheby
    0.49
    SupportActionBar
    0.48
    phalt
    0.47
    graphicx
    0.47
     bone
    0.43
    кор
    0.42
    Activations Density 0.323%

    No Known Activations