© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 10531
    Prev
    Next
    INDEX
    Explanations

    references to monetary values and fundraising amounts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    
    -0.59
    adaptiveStyles
    -0.53
    abstractmethod
    -0.48
     dente
    -0.48
    xo
    -0.48
     códigos
    -0.48
    codable
    -0.46
    PhysRevLett
    -0.45
     fréqu
    -0.45
     OGSÅ
    -0.44
    POSITIVE LOGITS
     AssemblyProduct
    0.65
     eventually
    0.62
    eventually
    0.60
    Cyfarwyddwr
    0.56
    WithMany
    0.55
     Eventually
    0.54
    Eventually
    0.54
    Viungo
    0.52
     getTotal
    0.52
     تضيفلها
    0.52
    Activations Density 0.295%

    No Known Activations