© 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. 1484
    Prev
    Next
    INDEX
    Explanations

    section headers or separators within a scientific paper

    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
     Euph
    -0.56
     isolated
    -0.53
     poffe
    -0.52
    jarah
    -0.51
     ſol
    -0.50
     lut
    -0.49
     Reſ
    -0.49
    取
    -0.48
    ſelves
    -0.48
    inorder
    -0.48
    POSITIVE LOGITS
    ⓧ
    0.85
     CreateTagHelper
    0.70
    rungsseite
    0.61
    Rüyada
    0.57
     EconPapers
    0.56
    AccessorTable
    0.56
    허
    0.56
    HtmlAttribute
    0.54
     vux
    0.54
     définiti
    0.52
    Activations Density 0.158%

    No Known Activations