© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 1975
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce or refer to significant concepts or entities

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Mercier
    -0.68
     Nomination
    -0.66
     CreateTagHelper
    -0.65
    isContained
    -0.65
     Roja
    -0.64
     uintptr
    -0.63
     nominate
    -0.62
     onCancelled
    -0.62
    sizeCache
    -0.62
     toJson
    -0.60
    POSITIVE LOGITS
    feira
    0.72
    você
    0.70
    tvguidetime
    0.69
    ști
    0.65
    teman
    0.64
     ngờ
    0.63
    șe
    0.63
    ți
    0.62
    omonas
    0.61
     ł
    0.60
    Activations Density 0.703%

    No Known Activations