© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 3081
    Prev
    Next
    INDEX
    Explanations

    tokens that represent references to lists and figures

    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
    Negative Logits
    Personensuche
    -0.65
     للمعارف
    -0.56
    MemoryWarning
    -0.54
     kteří
    -0.52
    +:+
    -0.52
     Roskov
    -0.51
    っこう
    -0.51
    afficheront
    -0.49
    urezza
    -0.49
    }();
    -0.48
    POSITIVE LOGITS
    第
    1.09
     Episode
    1.08
     #
    1.06
     Part
    0.96
    Episode
    0.93
     Chapter
    0.93
     Item
    0.93
     episode
    0.93
     Module
    0.92
     Day
    0.91
    Activations Density 2.084%

    No Known Activations