© 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. 32357
    Prev
    Next
    INDEX
    Explanations

    references to immunological signaling pathways and related proteins

    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
    nextProps
    -1.12
     houſe
    -1.02
     MainAxisSize
    -1.02
     Perſ
    -0.99
     itſelf
    -0.98
     Houſe
    -0.98
     Jefus
    -0.98
    Jeografia
    -0.96
     Persians
    -0.92
    vedev
    -0.90
    POSITIVE LOGITS
     IS
    1.07
    IS
    0.83
     iz
    0.72
    ISL
    0.72
     Dov
    0.71
     ARE
    0.71
     Is
    0.66
    ARE
    0.65
    ization
    0.64
    ⎯
    0.63
    Activations Density 0.023%

    No Known Activations