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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14812
    Prev
    Next
    INDEX
    Explanations

    the presence of viral particles or nucleic acid content within plasma or viral preparations

    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
    WT
    -0.84
     autorytatywna
    -0.65
    SizeF
    -0.62
    nadequate
    -0.60
    Референце
    -0.60
    Дереккөздер
    -0.59
    xtext
    -0.59
     HasFactory
    -0.59
     Houſe
    -0.58
    IFICATE
    -0.57
    POSITIVE LOGITS
    wt
    2.05
     wt
    2.00
     Wt
    0.84
    Wt
    0.82
    
    0.78
     nakalista
    0.74
    onomia
    0.60
    wts
    0.59
    vol
    0.55
     vol
    0.53
    Activations Density 0.003%

    No Known Activations