© 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. 18-RES-MATRYOSHKA-DC
    7. 973
    Prev
    Next
    INDEX
    Explanations

    code snippets, issue reports, and the word "patch"

    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.18.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.18.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
     estimés
    -0.60
     lateinit
    -0.58
    CppMethod
    -0.57
    runApp
    -0.57
     internet
    -0.55
     nonatomic
    -0.54
     awakeFromNib
    -0.52
    исленность
    -0.50
    Hozzáférés
    -0.50
    Chooser
    -0.50
    POSITIVE LOGITS
     bug
    1.00
     Bug
    0.97
    Bug
    0.93
    bug
    0.92
    fixes
    0.81
    BUG
    0.80
    bugs
    0.79
     Fixing
    0.79
     bugs
    0.78
     fixes
    0.77
    Activations Density 1.139%

    No Known Activations