© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4849
    Prev
    Next
    INDEX
    Explanations

    references to text formatting styles such as bold, italics, and font weight

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.73
    IonicModule
    -0.72
     ProtoMessage
    -0.70
    حياته
    -0.68
    opsida
    -0.68
     utafitiHapana
    -0.68
    Tembelea
    -0.67
    FieldDescriptor
    -0.67
    Vidite
    -0.67
     TextEditing
    -0.66
    POSITIVE LOGITS
     Bold
    3.17
     bold
    3.08
    Bold
    3.03
    bold
    3.02
     BOLD
    2.50
    BOLD
    2.45
     boldness
    2.34
     boldly
    2.27
     bolder
    2.16
     daring
    1.75
    Activations Density 0.066%

    No Known Activations