© 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. 22-RES-MATRYOSHKA-DC
    7. 3303
    Prev
    Next
    INDEX
    Explanations

    the definite article "the" and the preposition "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.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     virginity
    -0.61
     snowboarding
    -0.56
     obsidian
    -0.56
     smokers
    -0.56
     Tuberculosis
    -0.55
     slimming
    -0.55
     childbirth
    -0.54
     cremation
    -0.54
     aborted
    -0.52
     piped
    -0.52
    POSITIVE LOGITS
     other
    0.72
     most
    0.66
     dieux
    0.65
     following
    0.62
     autre
    0.61
    odule
    0.59
     chi̍t
    0.58
     fjor
    0.57
     وسلم
    0.57
    PreExecute
    0.57
    Activations Density 0.844%

    No Known Activations