© 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. 22403
    Prev
    Next
    INDEX
    Explanations

    details about artistic techniques and materials used in creative projects

    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
     дописавши
    -0.90
     CreateTagHelper
    -0.84
    RenderAtEndOf
    -0.81
    RectangleBorder
    -0.72
    rungsseite
    -0.70
     BorderSide
    -0.66
     مشين
    -0.66
    adaptiveStyles
    -0.65
     visuales
    -0.65
    DrawerToggle
    -0.65
    POSITIVE LOGITS
    providedIn
    0.73
     layering
    0.50
     layer
    0.46
    ovem
    0.44
    رحلة
    0.43
    unków
    0.43
     Layer
    0.43
    撒
    0.43
     spent
    0.43
    ленко
    0.42
    Activations Density 0.041%

    No Known Activations