© 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. 12-RES-MATRYOSHKA-DC
    7. 17273
    Prev
    Next
    INDEX
    Explanations

    text formatting commands, specifically those indicating bold or emphasized text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    matchCondition
    -0.81
    سال
    -0.78
     كومونز
    -0.76
     Sanderson
    -0.75
    WriteTagHelper
    -0.75
    ंदीखरीदारी
    -0.72
    ResumeLayout
    -0.71
    SourceChecksum
    -0.66
    migrationBuilder
    -0.66
     Ronan
    -0.66
    POSITIVE LOGITS
    textbf
    2.02
    textit
    0.90
     iſt
    0.81
    bibfield
    0.78
    HTT
    0.75
    bibinfo
    0.73
     Eſ
    0.73
     Reſ
    0.73
    ็จ
    0.72
     Anſ
    0.72
    Activations Density 0.001%

    No Known Activations