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. 9-RES-MATRYOSHKA-DC
    4. 16741
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "out", and negative phrases like "not to".

    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
    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
    //
    -0.55
     notes
    -0.51
    afa
    -0.50
     Walkover
    -0.50
    hangi
    -0.50
    luan
    -0.49
    anteen
    -0.49
    phosa
    -0.49
    wikimedia
    -0.48
     note
    -0.47
    POSITIVE LOGITS
     esternos
    0.68
     resourceCulture
    0.66
    IUrlHelper
    0.66
     <<<<<<<<<<<<<<
    0.65
     <=",
    0.65
     typelib
    0.62
    sizeCache
    0.60
    tvguidetime
    0.60
    CodeAttribute
    0.57
     estekak
    0.57
    Activations Density 0.145%

    No Known Activations