© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13699
    Prev
    Next
    INDEX
    Explanations

    numerical patterns involving large negative or high magnitude numbers

    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
     
    -0.57
    Slf
    -0.52
    ']))
    
    -0.52
    ]='\
    -0.50
    igshid
    -0.49
      
    -0.49
     </
    -0.48
     continúas
    -0.48
    artifactId
    -0.47
    AppMethodBeat
    -0.47
    POSITIVE LOGITS
    WriteTagHelper
    0.87
     تضيفلها
    0.82
     $+
    0.70
     ویکی‌پدی
    0.69
    ,+
    0.68
      (
    0.67
    OrEqual
    0.64
     médicaux
    0.62
     fossa
    0.62
    .+
    0.61
    Activations Density 0.124%

    No Known Activations