© 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. 2957
    Prev
    Next
    INDEX
    Explanations

    references to outside sources in the format CR## or B##

    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
     intptr
    -0.66
    ("")]
    -0.65
    tonode
    -0.62
    <?
    -0.61
    Constantes
    -0.57
    nodoc
    -0.53
     awakeFromNib
    -0.51
    ViewFeatures
    -0.50
    ANTLR
    -0.49
    *)(
    -0.49
    POSITIVE LOGITS
     [
    0.71
    LabelTagHelper
    0.70
    UnsafeEnabled
    0.68
    InputTagHelper
    0.54
    }\]
    0.53
    [
    0.53
    IBarButtonItem
    0.52
    רושלים
    0.51
     kasarigan
    0.50
     Савезне
    0.50
    Activations Density 0.098%

    No Known Activations