© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13954
    Prev
    Next
    INDEX
    Explanations

    references to specific high-intensity white noise or filter parameters used in signal processing

    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
     scolas
    -0.66
     pageContext
    -0.62
    tagext
    -0.61
     barbati
    -0.59
     Hentet
    -0.57
    Soda
    -0.57
    phens
    -0.55
     postale
    -0.54
    Népesség
    -0.54
    ossa
    -0.53
    POSITIVE LOGITS
    uren
    0.84
     Alg
    0.78
    rophi
    0.77
    WHM
    0.69
    Alg
    0.68
    Deal
    0.68
     kry
    0.67
    ursal
    0.66
     Deal
    0.65
     صوتيه
    0.64
    Activations Density 0.084%

    No Known Activations