© 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. 2455
    Prev
    Next
    INDEX
    Explanations

    questions in documentation asking for actions the reader should perform

    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
    <?
    -0.66
    出版年
    -0.64
    LookAnd
    -0.61
     dịch
    -0.58
    avras
    -0.58
    IContainer
    -0.56
    ünst
    -0.56
     VISUAL
    -0.56
    ướ
    -0.53
    CppMethod
    -0.53
    POSITIVE LOGITS
    Personensuche
    0.69
    MemoryWarning
    0.52
    nocchi
    0.51
    :✨
    0.49
    patine
    0.48
     lượng
    0.47
    enumi
    0.44
    antwoorde
    0.44
    AtIndexPath
    0.43
    "$_
    0.43
    Activations Density 0.015%

    No Known Activations