© 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. 25942
    Prev
    Next
    INDEX
    Explanations

    intense emotional or physical states often depicted metaphorically

    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
    rrggbb
    -0.89
    sizeCache
    -0.89
    parsedMessage
    -0.88
    StoryboardSegue
    -0.82
     analogy
    -0.76
    
    -0.74
    principalColumn
    -0.70
    RectangleBorder
    -0.68
     analogies
    -0.65
    kuuta
    -0.63
    POSITIVE LOGITS
    хва
    0.48
    :][
    0.46
    下的
    0.45
     Says
    0.45
    atics
    0.45
     says
    0.43
    fasst
    0.43
     yaptığı
    0.43
     verá
    0.42
     zegt
    0.42
    Activations Density 0.042%

    No Known Activations