© 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
    2. Gemma-2-2B
    3. 18-RES-MATRYOSHKA-DC
    4. 463
    Prev
    Next
    INDEX
    Explanations

    XML-like code containing data type definitions and descriptions of data elements

    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
    ↵↵
    -0.60
     ๆ
    -0.46
    namespace
    -0.45
    ๆ
    -0.44
    if
    -0.44
    //
    -0.44
    archiviato
    -0.43
    ()
    -0.43
    PhysRev
    -0.41
    anga
    -0.41
    POSITIVE LOGITS
    -<
    0.94
    <
    0.90
    :<
    0.85
     $<$
    0.84
     <
    0.83
     EconPapers
    0.83
    )<
    0.82
    <table>
    0.80
     виправивши
    0.80
    !<
    0.79
    Activations Density 1.312%

    No Known Activations