© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 31803
    Prev
    Next
    INDEX
    Explanations

    instances of significant numerical values or quantities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     ſame
    -0.69
     houſe
    -0.69
     purpoſe
    -0.68
     ſtate
    -0.67
     ſever
    -0.66
     ―――――
    -0.64
    сылкі
    -0.63
     Anſ
    -0.62
     Houſe
    -0.62
     opér
    -0.61
    POSITIVE LOGITS
     imageNamed
    0.66
    enumi
    0.66
     propOrder
    0.61
     jScrollPane
    0.55
     चुनें
    0.54
    enumii
    0.54
    $_['
    0.52
     class
    0.50
    fjspx
    0.50
     K
    0.50
    Activations Density 0.008%

    No Known Activations