© 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. 22-RES-MATRYOSHKA-DC
    7. 2491
    Prev
    Next
    INDEX
    Explanations

    sentences that describe figures or tables typically found in scientific 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
     discussed
    -0.77
     discussion
    -0.73
     above
    -0.71
    Discuss
    -0.70
     discusses
    -0.69
     Discus
    -0.68
    Discussion
    -0.66
     Réponses
    -0.66
     discussions
    -0.66
    mentioned
    -0.66
    POSITIVE LOGITS
     shown
    0.83
    SourceChecksum
    0.71
    tagHelperRunner
    0.68
     Shown
    0.60
    expandindo
    0.59
    tagext
    0.58
    shown
    0.54
     mostrado
    0.53
     نمایش
    0.53
     Display
    0.52
    Activations Density 0.105%

    No Known Activations