© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1036
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of mechanical and electrical inventions, particularly those involving components and motion

    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
    PyExc
    -0.64
    reportWebVitals
    -0.58
    AtIndexPath
    -0.57
     karna
    -0.57
     Automatic
    -0.57
    glMatrixMode
    -0.56
    __(/*!
    -0.56
     desired
    -0.55
    SpringRunner
    -0.54
     patented
    -0.54
    POSITIVE LOGITS
     arranged
    0.59
    Jeografia
    0.58
    HasForeignKey
    0.56
     connect
    0.55
    NameInMap
    0.55
     Arranged
    0.54
     connected
    0.54
     conecta
    0.52
    __':
    0.51
    rece
    0.51
    Activations Density 0.865%

    No Known Activations