© 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. 18671
    Prev
    Next
    INDEX
    Explanations

    phrases or questions relating to probabilistic calculations or probabilities involving letter selections

    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
    InitVars
    -0.80
    TagMode
    -0.67
    ViewFeatures
    -0.60
     Réponses
    -0.59
    WindowConstants
    -0.59
    AutoScale
    -0.59
     sooner
    -0.57
     createSprite
    -0.57
     الاطلاع
    -0.55
     chút
    -0.55
    POSITIVE LOGITS
    Einzelnachweise
    0.72
    
    0.70
    Bronnen
    0.65
     ChromeDriver
    0.56
    multirow
    0.55
     wies
    0.55
    ofan
    0.50
    XmlAccessType
    0.49
     validamos
    0.49
    ograf
    0.49
    Activations Density 0.002%

    No Known Activations