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. 30419
    Prev
    Next
    INDEX
    Explanations

    the words "Notes" and "References"

    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
    andaag
    -0.62
     Lugar
    -0.58
     Galbraith
    -0.57
     насељу
    -0.56
    втра
    -0.55
     Marchand
    -0.54
    Portály
    -0.54
     néglig
    -0.54
    //
    -0.53
    MultipartFile
    -0.53
    POSITIVE LOGITS
    Notes
    0.81
     Notes
    0.72
    NOTES
    0.69
    notes
    0.64
     notes
    0.60
    Salta
    0.58
     ProtoMessage
    0.57
     NOTES
    0.56
    GeneratedMessage
    0.55
    Notas
    0.54
    Activations Density 0.037%

    No Known Activations