© 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. 709
    Prev
    Next
    INDEX
    Explanations

    articles, pronouns, and adjectives that commonly appear in research papers

    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
     }^{[
    -0.61
     referenties
    -0.52
     gian
    -0.52
    tifiable
    -0.50
     industry
    -0.47
    φι
    -0.47
     raz
    -0.47
    学ぶ
    -0.47
     #
    -0.45
    ONY
    -0.45
    POSITIVE LOGITS
     discorso
    0.73
     conclusion
    0.70
     argument
    0.70
     expression
    0.69
    vábbi
    0.68
     createSlice
    0.67
    conclusion
    0.64
    Поздрав
    0.64
    localctx
    0.64
     conclusions
    0.64
    Activations Density 1.019%

    No Known Activations