© 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. 853
    Prev
    Next
    INDEX
    Explanations

    mentions of edits needing to be made

    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
    jsonwebtoken
    -0.61
    bable
    -0.48
    urcht
    -0.46
    ovsk
    -0.45
    runApp
    -0.45
     /^[
    -0.45
    hearsed
    -0.44
    glBegin
    -0.41
    öp
    -0.40
    ARROLLO
    -0.40
    POSITIVE LOGITS
     changes
    2.34
     modification
    2.22
     modifications
    2.22
     change
    2.17
     changed
    2.06
     alterations
    2.05
     alteration
    2.00
     Changes
    1.99
     modify
    1.95
    changes
    1.95
    Activations Density 4.157%

    No Known Activations