© 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. 25979
    Prev
    Next
    INDEX
    Explanations

    quantitative measures and results related to efficiency and yield in scientific contexts

    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
    StructEnd
    -0.61
    
    -0.61
    RegressionTest
    -0.60
     تضيفلها
    -0.56
     écart
    -0.56
    utiny
    -0.55
     Wikimédia
    -0.55
    GEBURTSDATUM
    -0.55
    IndentedString
    -0.55
     שוליים
    -0.54
    POSITIVE LOGITS
     efficiency
    0.67
     efficiencies
    0.64
     effic
    0.59
     efficient
    0.58
    delig
    0.57
     (%)
    0.55
    podar
    0.54
     effici
    0.54
    ScopeManager
    0.53
    Recu
    0.53
    Activations Density 0.088%

    No Known Activations