© 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. 1450
    Prev
    Next
    INDEX
    Explanations

    references to figures or tables 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
    الإنجليزية
    -0.83
     مشين
    -0.82
    styleType
    -0.76
    LookAnd
    -0.76
     насељу
    -0.72
     }</
    -0.68
    ="#"><
    -0.65
    errHandler
    -0.65
    μβρίου
    -0.64
    ViewFeatures
    -0.63
    POSITIVE LOGITS
      
    0.84
     doubtnut
    0.74
     africain
    0.61
    ourites
    0.58
    ########.
    0.58
     ROOMS
    0.57
     dandy
    0.56
     setUsername
    0.56
     vectorielles
    0.56
    helves
    0.56
    Activations Density 0.362%

    No Known Activations