Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-RES-MATRYOSHKA-DC
    4. 31
    Prev
    Next
    INDEX
    Explanations

    references to the word "with."

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onOptions
    -0.77
    ReactDOM
    -0.69
    DispatchToProps
    -0.69
    assertArray
    -0.69
    Isle
    -0.69
    migrationBuilder
    -0.68
    jago
    -0.66
     putea
    -0.66
    Acts
    -0.65
    ayana
    -0.65
    POSITIVE LOGITS
     with
    2.47
    with
    2.23
     With
    2.16
     WITH
    2.16
    With
    1.95
     avec
    1.89
    WITH
    1.80
     Avec
    1.64
    Avec
    1.60
     dengan
    1.48
    Activations Density 4.187%

    No Known Activations