© 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. 28720
    Prev
    Next
    INDEX
    Explanations

    instances of the word "although."

    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
     nonetheless
    -0.69
     gynhyrchwyd
    -0.67
    Nonetheless
    -0.65
     esfuerzos
    -0.65
     nevertheless
    -0.64
     comunque
    -0.64
    Nevertheless
    -0.63
     néanmoins
    -0.62
     nonostante
    -0.61
     despite
    -0.61
    POSITIVE LOGITS
    fordable
    0.70
    urne
    0.70
    aults
    0.70
    iastical
    0.69
    DataBean
    0.69
    roleum
    0.68
    polation
    0.66
    andum
    0.65
    .}~\
    0.65
    prüche
    0.65
    Activations Density 0.016%

    No Known Activations