© 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. 24-RES-MATRYOSHKA-DC
    7. 636
    Prev
    Next
    INDEX
    Explanations

    biochemical and scientific terminology, especially related to carbohydrates, glycosylation, and molecular structures.

    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.24.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.24.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
    enfone
    -0.62
     crack
    -0.59
     فريبيس
    -0.57
    kloped
    -0.57
     CRACK
    -0.55
     Ask
    -0.51
    ẨM
    -0.51
    assertRaises
    -0.50
    SharedCtor
    -0.50
    QPalette
    -0.50
    POSITIVE LOGITS
     sugar
    0.76
    sugar
    0.69
     Sugar
    0.68
    Sugar
    0.68
     sugars
    0.68
    manan
    0.64
     SUGAR
    0.62
     fu
    0.61
     man
    0.61
     mann
    0.61
    Activations Density 0.508%

    No Known Activations