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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11073
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers or references in a technical document

    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
    +#+
    -0.77
     समीक्षक
    -0.74
    IVEREF
    -0.71
     AssemblyCompany
    -0.60
     betweenstory
    -0.60
     оригіналу
    -0.59
     miele
    -0.57
     Commencez
    -0.56
    skraft
    -0.56
     CiNii
    -0.56
    POSITIVE LOGITS
    }}}}
    0.60
     }}"></
    0.57
    "]]
    0.56
     Pizz
    0.56
    delijk
    0.55
    aarrggbb
    0.55
    Géographie
    0.54
    ähn
    0.53
     Gle
    0.53
     تضيفلها
    0.53
    Activations Density 0.003%

    No Known Activations