© 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. 9066
    Prev
    Next
    INDEX
    Explanations

    references to dietary components, particularly unhealthy foods and beverages

    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
    EReference
    -0.64
    BASEPATH
    -0.59
    GenerationType
    -0.58
    cshtml
    -0.57
    
    -0.56
     Provision
    -0.54
    UserScript
    -0.53
    HasAnnotation
    -0.53
    amarin
    -0.52
     Continuity
    -0.50
    POSITIVE LOGITS
     betweenstory
    0.58
    addContainerGap
    0.53
    жли
    0.53
     cardíaca
    0.49
    apimachinery
    0.47
     AppCompatTheme
    0.47
     initComponents
    0.47
     hígado
    0.46
    THISDAY
    0.46
     azon
    0.46
    Activations Density 0.027%

    No Known Activations