© 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. 12-RES-MATRYOSHKA-DC
    7. 12278
    Prev
    Next
    INDEX
    Explanations

    specific formatting styles or attributes related to text presentation, particularly around font styling

    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
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.51
    捻
    -0.50
    findpost
    -0.49
    (/[
    -0.49
    luste
    -0.48
    CodeAnalysis
    -0.46
     cellspacing
    -0.46
     average
    -0.45
     Sgt
    -0.45
    Šaltiniai
    -0.45
    POSITIVE LOGITS
    PerformLayout
    0.66
    aarrggbb
    0.66
    cinia
    0.65
    amazonaws
    0.64
     bpy
    0.64
     المعيارى
    0.61
    ंदीखरीदारी
    0.60
    ReusableCell
    0.60
     PDR
    0.60
    SBATCH
    0.60
    Activations Density 0.004%

    No Known Activations