© 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. 25875
    Prev
    Next
    INDEX
    Explanations

    phrases relating to data transfer and connections

    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
     Zahl
    -0.47
    usda
    -0.44
     enf
    -0.43
     par
    -0.43
     domestic
    -0.42
    readAs
    -0.42
     Mich
    -0.42
     joining
    -0.42
     Cooke
    -0.40
     return
    -0.39
    POSITIVE LOGITS
    UserScript
    0.88
    enumii
    0.88
     Chwiliwch
    0.83
     contextLoads
    0.81
    RenderAtEndOf
    0.81
     мәкал
    0.79
    enumi
    0.78
    الحياه
    0.78
    AddTagHelper
    0.77
     Infórmanos
    0.77
    Activations Density 0.061%

    No Known Activations