© 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. 32541
    Prev
    Next
    INDEX
    Explanations

    sequences or patterns that indicate quantities or measurements in a data-driven context

    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
     Besøkt
    -0.67
    Geplaatst
    -0.63
     RouterModule
    -0.63
     understatement
    -0.60
     Beren
    -0.59
     angina
    -0.58
    ValueStyle
    -0.57
    MeasureSpec
    -0.56
    matchCondition
    -0.56
     IOException
    -0.56
    POSITIVE LOGITS
    /**
    0.60
    kilde
    0.56
     Italijani
    0.56
    GeoNames
    0.55
    cifix
    0.54
    inais
    0.52
    fscanf
    0.51
     figure
    0.51
     null
    0.50
     figures
    0.50
    Activations Density 0.010%

    No Known Activations