© 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. 2702
    Prev
    Next
    INDEX
    Explanations

    numerical data and specific formatting patterns within the 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
    Not in Any Lists

    No Comments

    Negative Logits
    doo
    -0.53
    ложений
    -0.53
     Parr
    -0.52
     appearance
    -0.51
    ریق
    -0.51
     seguintes
    -0.51
     dėl
    -0.51
    ungkapkan
    -0.50
     attempted
    -0.49
     shrine
    -0.49
    POSITIVE LOGITS
    MemoryWarning
    0.94
    ReusableCell
    0.88
    تقاوى
    0.85
    存于互联网档案馆
    0.84
    RenderAtEndOf
    0.80
    FXMLLoader
    0.79
    UpInside
    0.78
    ChildScrollView
    0.77
    SequentialGroup
    0.76
    ddots
    0.75
    Activations Density 0.762%

    No Known Activations