© 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. 18-RES-MATRYOSHKA-DC
    7. 1489
    Prev
    Next
    INDEX
    Explanations

    the word "both", especially when followed by "of"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    fjspx
    -0.73
     qualunque
    -0.65
    rdoba
    -0.63
     Efq
    -0.63
     magari
    -0.62
     архивлан
    -0.61
    ,:);
    -0.60
    jmniej
    -0.60
    seamnă
    -0.60
    Alguien
    -0.60
    POSITIVE LOGITS
     sides
    1.25
     sexes
    0.96
     halves
    0.88
    sides
    0.87
     ends
    0.85
     Sides
    0.82
    enumi
    0.79
     side
    0.75
     parties
    0.73
    Sides
    0.70
    Activations Density 0.214%

    No Known Activations