© 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. 24-RES-MATRYOSHKA-DC
    7. 1641
    Prev
    Next
    INDEX
    Explanations

    the word "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.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    both
    -0.70
     both
    -0.69
     some
    -0.63
     all
    -0.61
     wszyscy
    -0.58
     each
    -0.57
     another
    -0.57
    eseorang
    -0.57
     algum
    -0.56
    Both
    -0.55
    POSITIVE LOGITS
     them
    0.94
     these
    0.89
     us
    0.89
     chúng
    0.83
    them
    0.82
     esos
    0.77
    these
    0.73
     those
    0.71
     ellos
    0.68
     ujednoznacz
    0.67
    Activations Density 0.232%

    No Known Activations