© 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. 877
    Prev
    Next
    INDEX
    Explanations

    numbers, particularly those related to statistics or measurements

    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
     forty
    -0.71
     seventy
    -0.68
    Autoritní
    -0.64
    EndGlobalSection
    -0.63
     sixty
    -0.62
     بيها
    -0.62
    forty
    -0.61
    argout
    -0.60
     fifty
    -0.60
    Хьажоргаш
    -0.60
    POSITIVE LOGITS
     שוליים
    0.68
    fromnode
    0.57
     boto
    0.57
    千
    0.57
     thousand
    0.56
     千
    0.50
     Component
    0.48
     Mille
    0.48
     אל
    0.47
    三千
    0.47
    Activations Density 0.651%

    No Known Activations