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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 30527
    Prev
    Next
    INDEX
    Explanations

    the word "anticoagulant" and related terms.

    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
     purpoſe
    -0.99
    Rujuakan
    -0.83
    couvrez
    -0.83
     itſelf
    -0.82
     Reſ
    -0.82
     Lichten
    -0.82
     Balo
    -0.79
     Diſ
    -0.77
     Majefty
    -0.77
     Dami
    -0.77
    POSITIVE LOGITS
    farin
    1.63
     anticoag
    1.61
    antico
    0.59
    WRITER
    0.57
    divarius
    0.56
    endsection
    0.52
    </caption>
    0.51
    styleType
    0.50
    annotation
    0.50
     Kew
    0.48
    Activations Density 0.001%

    No Known Activations