© 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. 8839
    Prev
    Next
    INDEX
    Explanations

    instances of significant surprises or noteworthy findings

    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
     ActionResult
    -0.52
    tences
    -0.47
    mipmap
    -0.47
    msgSender
    -0.47
    QtWidgets
    -0.46
    <%@
    -0.44
    toolStripButton
    -0.42
    IActionResult
    -0.42
     SafeMath
    -0.42
     legal
    -0.41
    POSITIVE LOGITS
    AsUp
    0.85
     utafitiHapana
    0.82
    Jereo
    0.78
     ویکی‌پدی
    0.77
     propOrder
    0.70
     CreateTagHelper
    0.69
     SwitchCompat
    0.69
     EconPapers
    0.68
    fjspx
    0.68
    setof
    0.67
    Activations Density 1.421%

    No Known Activations