© 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. 2267
    Prev
    Next
    INDEX
    Explanations

    the letter "c" followed by the letters "iting"

    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
    PhysRev
    -0.56
    ViewImports
    -0.50
    لينكات
    -0.49
    awtextra
    -0.48
    BagLayout
    -0.48
     Corm
    -0.47
    petal
    -0.45
    ALLENG
    -0.44
    Viitteet
    -0.44
    FunctionFlags
    -0.43
    POSITIVE LOGITS
    
    0.60
     vergessen
    0.57
    новниш
    0.56
    するに
    0.55
    oncé
    0.55
     يكن
    0.55
    COUVER
    0.54
    InitVars
    0.53
    ///</
    0.52
    theless
    0.51
    Activations Density 0.109%

    No Known Activations