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. 22
    Prev
    Next
    INDEX
    Explanations

    comments related to 'other' or unspecified additional information

    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
     للاسماء
    -0.79
     vectorielles
    -0.77
    infeld
    -0.69
     ویکی‌پدیا
    -0.68
     Francine
    -0.68
     vectorielle
    -0.66
    inkas
    -0.66
    rangian
    -0.65
     assoluto
    -0.62
     NgModule
    -0.61
    POSITIVE LOGITS
     other
    2.91
    other
    2.61
    Other
    2.56
     Other
    2.53
     OTHER
    2.44
    autres
    2.27
    OTHER
    2.25
     autres
    2.16
     outros
    2.08
     otros
    2.06
    Activations Density 3.468%

    No Known Activations