© 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. 2054
    Prev
    Next
    INDEX
    Explanations

    math problems asking to calculate the greatest common factor or divisor, matching keywords like "highest", "greatest", "common", "factor", and "divisor".

    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
    دانشنامهٔ
    -0.56
    \}^{
    -0.52
     doubles
    -0.52
    diq
    -0.50
     placebo
    -0.47
     Doubles
    -0.47
     Better
    -0.47
    IImage
    -0.46
     BETTER
    -0.46
     deflation
    -0.46
    POSITIVE LOGITS
     common
    1.38
    common
    1.15
     Common
    1.09
    Common
    1.04
     común
    1.02
     communs
    0.90
     COMMON
    0.88
     comunes
    0.88
    COMMON
    0.86
     comum
    0.85
    Activations Density 0.119%

    No Known Activations