© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 15199
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the."

    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
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.57
     Meksiku
    -0.56
     other
    -0.54
    rasil
    -0.54
    مئ
    -0.50
    rav
    -0.49
     savez
    -0.49
     cả
    -0.48
    {-\
    -0.48
    CodeDom
    -0.47
    POSITIVE LOGITS
    ArgsConstructor
    0.66
    ActionCreators
    0.64
    bewerken
    0.64
     disponibilités
    0.63
     Bourgoin
    0.60
    posób
    0.60
     TextInputType
    0.58
    queryInterface
    0.58
     vectorielles
    0.57
     Autorisations
    0.57
    Activations Density 0.030%

    No Known Activations