© 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. 479
    Prev
    Next
    INDEX
    Explanations

    parenthetical expressions representing citations to academic journals or books

    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
    řes
    -0.57
    -------------</
    -0.56
     Euse
    -0.55
     uchiha
    -0.55
     Adjutant
    -0.55
     Prophe
    -0.54
     Darfur
    -0.53
     Pliny
    -0.52
     ikea
    -0.52
    cestry
    -0.52
    POSITIVE LOGITS
     Journal
    0.88
     journal
    0.81
     submitted
    0.77
     proceedings
    0.74
    Journal
    0.71
    accepted
    0.66
     Proceedings
    0.65
     J
    0.64
     accepted
    0.63
    arXiv
    0.61
    Activations Density 1.853%

    No Known Activations