© 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. 22-RES-MATRYOSHKA-DC
    7. 1709
    Prev
    Next
    INDEX
    Explanations

    numbers, especially those used in addresses, dates, laws, and mathematical formulas

    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.22.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.22.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
     متعلقه
    -0.88
     referenties
    -0.84
     للمعارف
    -0.78
    الإنجليزية
    -0.77
     AssemblyCompany
    -0.71
    OGND
    -0.70
     pinulongan
    -0.69
    awaiter
    -0.68
     Préférences
    -0.68
     kasarigan
    -0.67
    POSITIVE LOGITS
    simile
    0.52
     complètes
    0.49
     SVC
    0.47
    pgm
    0.46
    SVC
    0.45
    endpush
    0.44
     comigo
    0.42
     SCL
    0.42
     fermés
    0.41
     веке
    0.41
    Activations Density 1.325%

    No Known Activations