© 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. 3135
    Prev
    Next
    INDEX
    Explanations

    Latex math symbols.

    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
     **
    -0.58
    ob
    -0.54
    <strong>
    -0.52
     ${
    -0.52
    iar
    -0.51
     Rob
    -0.50
    <b>
    -0.50
     Mr
    -0.49
     Land
    -0.48
    ARS
    -0.48
    POSITIVE LOGITS
     resourceCulture
    1.25
    bootstrapcdn
    0.94
    uxxxx
    0.89
     CreateTagHelper
    0.88
    alpha
    0.87
     tartalomajánló
    0.83
    beta
    0.82
    webElementGuid
    0.79
    setVerticalGroup
    0.77
    ImageContext
    0.77
    Activations Density 0.396%

    No Known Activations