© 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. 1039
    Prev
    Next
    INDEX
    Explanations

    code snippets containing identifiers with underscores

    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
    stackSize
    -0.62
     yonder
    -0.61
    __(/*!
    -0.59
    (
    -0.59
     whither
    -0.57
    hips
    -0.56
     $("<
    -0.56
    {
    -0.54
     screenWidth
    -0.52
    ="#"><
    -0.51
    POSITIVE LOGITS
    &_
    1.11
     StatefulWidget
    0.81
     فريبيس
    0.78
    Manbalar
    0.77
    ?_
    0.75
     StatelessWidget
    0.72
    @_
    0.69
     թվական
    0.68
    '_
    0.66
    AsUp
    0.65
    Activations Density 0.885%

    No Known Activations