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. 0-RES-MATRYOSHKA-DC
    4. 15062
    Prev
    Next
    INDEX
    Explanations

    references to the expression of specific genes or proteins

    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
    express
    -1.95
     express
    -1.92
     Express
    -1.89
    Express
    -1.88
     EXPRESS
    -1.56
    EXPRESS
    -1.49
     expressing
    -1.09
     expresses
    -1.00
    expressing
    -0.98
    xpress
    -0.96
    POSITIVE LOGITS
     expressed
    0.67
    énario
    0.55
    expressed
    0.50
     insisted
    0.50
     assoluto
    0.49
    هر
    0.48
    SpringBoot
    0.48
     zasi
    0.47
     said
    0.47
     surla
    0.47
    Activations Density 0.007%

    No Known Activations