© 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. 422
    Prev
    Next
    INDEX
    Explanations

    code snippets, versions, or numerical references within documents

    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
    awtextra
    -0.68
     eighteenth
    -0.57
     Eighteen
    -0.54
     Eighteenth
    -0.54
     fourteenth
    -0.53
     fourteen
    -0.50
    Brother
    -0.50
     centenary
    -0.50
     gatto
    -0.49
     Thirteenth
    -0.49
    POSITIVE LOGITS
    5
    1.63
     fifth
    1.47
     five
    1.41
     Fifth
    1.41
     FIVE
    1.27
     Five
    1.26
    Fifth
    1.26
    ５
    1.25
    五
    1.25
    five
    1.20
    Activations Density 3.107%

    No Known Activations