© 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. 15351
    Prev
    Next
    INDEX
    Explanations

    structures quantifying divisions or classifications within data points or parameters

    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
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.67
     Divide
    -0.60
     divided
    -0.59
    huk
    -0.58
     divis
    -0.57
     divide
    -0.57
     Divided
    -0.57
    OMB
    -0.55
     divides
    -0.54
     divisions
    -0.54
    POSITIVE LOGITS
     تضيفلها
    0.88
    Personensuche
    0.75
    tanleria
    0.69
    bewerken
    0.63
     betweenstory
    0.62
    🔈
    0.62
     financières
    0.60
     judiciaire
    0.58
     îna
    0.56
     dobrý
    0.56
    Activations Density 0.023%

    No Known Activations