© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 885
    Prev
    Next
    INDEX
    Explanations

    angle brackets, less than signs, and other code syntax

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     abuse
    -0.53
     Abuse
    -0.50
     Cuff
    -0.48
     abused
    -0.48
     Goode
    -0.47
    endsection
    -0.47
     Overton
    -0.47
     biografias
    -0.47
     Lorna
    -0.46
    retung
    -0.46
    POSITIVE LOGITS
     build
    1.04
     Build
    0.99
    Build
    0.98
     BUILD
    0.96
    build
    0.94
     builds
    0.84
    EndGlobalSection
    0.78
    BUILD
    0.76
     building
    0.75
     Builds
    0.73
    Activations Density 0.959%

    No Known Activations