© 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. 29740
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific measurement and reference data in an experimental or theoretical context

    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
    PerformLayout
    -0.64
    :✨
    -0.58
    IsPostBack
    -0.57
    httphttps
    -0.53
    oneofs
    -0.51
    esez
    -0.50
    enterOuterAlt
    -0.50
    }\|
    -0.48
    coglie
    -0.48
     AssemblyTitle
    -0.47
    POSITIVE LOGITS
    χρι
    0.57
    thora
    0.57
     kentang
    0.57
     impresión
    0.56
    πως
    0.54
    tagHelperRunner
    0.53
     choix
    0.52
    LU
    0.52
     pungkasnya
    0.51
    limit
    0.48
    Activations Density 0.149%

    No Known Activations