© 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. 18901
    Prev
    Next
    INDEX
    Explanations

    protein interaction details and specific amino acid residues involved in molecular processes

    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
     متعلقه
    -0.74
    ValueStyle
    -0.70
    IVEREF
    -0.63
     iprot
    -0.61
     cref
    -0.60
    Hochspringen
    -0.57
    
    -0.55
     TType
    -0.54
    ❋
    -0.53
     ddelweddau
    -0.52
    POSITIVE LOGITS
     Efq
    0.72
    enumi
    0.70
     Theſe
    0.65
     löytyy
    0.64
     يتيمه
    0.63
     theſe
    0.61
     ſeveral
    0.61
     whoſe
    0.60
     ſmall
    0.60
     Anſ
    0.60
    Activations Density 0.011%

    No Known Activations