© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11445
    Prev
    Next
    INDEX
    Explanations

    structured data identifiers and status codes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    Viitteet
    -0.59
    InvalidProtocol
    -0.58
     kaarangay
    -0.57
    ViewFeatures
    -0.56
     ResponseEntity
    -0.55
     Paglinawan
    -0.55
    Посилання
    -0.54
    Становништво
    -0.54
    الإنجليزية
    -0.54
     virtuel
    -0.54
    POSITIVE LOGITS
     Iw
    0.54
    vogel
    0.49
    koľvek
    0.48
     ion
    0.48
     characterizes
    0.48
    omeness
    0.47
    wür
    0.47
    stående
    0.47
    lum
    0.47
     Tisch
    0.46
    Activations Density 0.202%

    No Known Activations