© 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. 14967
    Prev
    Next
    INDEX
    Explanations

    actions and processes related to decision-making and problem-solving

    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
     main
    -0.77
     key
    -0.69
     reason
    -0.67
     biggest
    -0.62
     razón
    -0.60
     problem
    -0.58
     major
    -0.57
     главной
    -0.57
     aim
    -0.56
     haupts
    -0.56
    POSITIVE LOGITS
    expandindo
    0.91
     photolibrary
    0.66
     zacht
    0.65
     tasche
    0.64
     ModelExpression
    0.62
    XmlAccessType
    0.60
    tersebut
    0.59
    hmig
    0.58
    Cyfarwyddwr
    0.58
     hedges
    0.58
    Activations Density 0.092%

    No Known Activations