© 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. 15742
    Prev
    Next
    INDEX
    Explanations

    patterns related to compatibility metrics or comparisons between categories

    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
    AnchorStyles
    -0.75
    RegistryLite
    -0.67
     numberOfRows
    -0.66
    ChildScrollView
    -0.59
     BoxDecoration
    -0.58
     protoimpl
    -0.57
     MaterialApp
    -0.53
     NSCoder
    -0.52
     AdapterView
    -0.52
    
    -0.50
    POSITIVE LOGITS
     CURIAM
    0.79
    čaj
    0.46
     Permanente
    0.46
     án
    0.45
    apeake
    0.45
    ष्ठ
    0.45
    ië
    0.45
    imine
    0.44
     Toby
    0.44
    ymus
    0.44
    Activations Density 0.053%

    No Known Activations