© 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. 26741
    Prev
    Next
    INDEX
    Explanations

    multiplicative relationships or terms in mathematical expressions

    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
    IMPORTED
    -0.63
    IGraphics
    -0.57
    AddTagHelper
    -0.56
     ModelExpression
    -0.56
    +#+#
    -0.54
     <>",
    -0.52
     (°
    -0.50
     للاسماء
    -0.50
     كومونز
    -0.49
    getFullYear
    -0.49
    POSITIVE LOGITS
     فريبيس
    0.59
    Tikang
    0.56
     charité
    0.55
    nologue
    0.55
     Parigi
    0.52
    ตรี
    0.52
    peño
    0.50
     canoes
    0.50
     tibia
    0.49
    خار
    0.48
    Activations Density 0.024%

    No Known Activations