© 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. 1417
    Prev
    Next
    INDEX
    Explanations

    references to structured materials or related terminology in the context of scientific descriptions

    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
     repens
    -1.02
     veneta
    -0.87
    JspWriter
    -0.85
     GLP
    -0.85
     Alden
    -0.84
     Pei
    -0.83
     Velo
    -0.82
     Epist
    -0.81
     Yuma
    -0.81
     yaris
    -0.80
    POSITIVE LOGITS
     structure
    1.31
     structures
    1.27
    structures
    1.22
     Structure
    1.17
     Structures
    1.16
    structure
    1.15
     STRUCTURE
    1.13
    Structure
    1.10
    truct
    1.05
     Stru
    1.05
    Activations Density 0.175%

    No Known Activations