© 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. 2058
    Prev
    Next
    INDEX
    Explanations

    language related to academic publishing

    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
    report
    -0.50
    tut
    -0.49
    IUrlHelper
    -0.47
    Report
    -0.46
     Report
    -0.46
    tagHelperRunner
    -0.45
    thesis
    -0.45
     notas
    -0.45
    Thesis
    -0.44
    ätte
    -0.44
    POSITIVE LOGITS
     '\\;'
    0.94
     дописавши
    0.70
    JvmStatic
    0.66
     Seeder
    0.65
     iNdEx
    0.64
     Bentham
    0.64
     otev
    0.63
    expandindo
    0.62
    AsUp
    0.61
     BoxDecoration
    0.59
    Activations Density 0.289%

    No Known Activations