© 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. 28932
    Prev
    Next
    INDEX
    Explanations

    terms related to protein residues in biochemical contexts

    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
    ----</
    -0.77
    Sao
    -0.73
    Климат
    -0.72
    Jaz
    -0.72
    Източници
    -0.64
    orski
    -0.64
    Хьажоргаш
    -0.63
     محفوظة
    -0.63
    liesslich
    -0.63
     Simón
    -0.62
    POSITIVE LOGITS
     residues
    1.34
     residue
    1.32
     Residue
    1.30
    Residue
    1.23
     Resid
    1.13
    residue
    1.13
    
    0.81
    resid
    0.77
     Muta
    0.76
     judiciales
    0.72
    Activations Density 0.006%

    No Known Activations