© 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. 12-RES-MATRYOSHKA-DC
    7. 23810
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to systems and processes

    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
    ArgsConstructor
    -1.13
    IndentedString
    -1.13
     nahilalakip
    -1.10
     kasarigan
    -1.06
    تقاوى
    -1.06
    BeginContext
    -1.05
     ویکی‌پدیا
    -1.05
    Chham
    -1.01
    Datuak
    -1.00
    IVEREF
    -1.00
    POSITIVE LOGITS
     (
    0.47
     <
    0.43
    io
    0.43
    q
    0.41
     A
    0.40
    ,
    0.40
     on
    0.39
     them
    0.39
     w
    0.39
    X
    0.39
    Activations Density 0.271%

    No Known Activations