© 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. 22-RES-MATRYOSHKA-DC
    7. 387
    Prev
    Next
    INDEX
    Explanations

    math problems asking for the greatest common factor or divisor of two numbers

    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
    chtung
    -0.50
    StringField
    -0.47
    πι
    -0.47
     Cushing
    -0.46
     désolés
    -0.45
    LocalizedString
    -0.45
     +
    -0.44
     initiates
    -0.44
    Клуб
    -0.44
    弄
    -0.44
    POSITIVE LOGITS
    Datuak
    0.78
     pinulongan
    0.77
    oa̍t
    0.75
     least
    0.75
    RenderAtEndOf
    0.72
     numerus
    0.70
     Roskov
    0.69
    ⓧ
    0.68
     decimal
    0.68
    AndEndTag
    0.67
    Activations Density 2.318%

    No Known Activations