© 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. 14872
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "do" in various forms

    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
     sauvages
    -0.64
     étoile
    -0.63
     faciles
    -0.61
     humaines
    -0.60
     ulei
    -0.59
    able
    -0.58
    Dade
    -0.58
     šte
    -0.57
     ऐसा
    -0.56
     végétale
    -0.56
    POSITIVE LOGITS
    NameInMap
    0.85
    tonode
    0.82
     Normdatei
    0.75
     imageNamed
    0.73
    EndGlobalSection
    0.73
    wixt
    0.72
    StructEnd
    0.72
    NOPQRST
    0.69
    MarshalTo
    0.66
    ImageContext
    0.66
    Activations Density 0.034%

    No Known Activations