© 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. 31078
    Prev
    Next
    INDEX
    Explanations

    terms related to the process of refinement in scientific or technical contexts

    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
     Doubleday
    -0.69
     Gaj
    -0.67
     Cros
    -0.66
     Bogota
    -0.66
    cherichia
    -0.66
    Cros
    -0.65
     Bisch
    -0.65
    onika
    -0.63
     Dot
    -0.63
    Aa
    -0.63
    POSITIVE LOGITS
     refinement
    1.31
     refinements
    1.31
     refine
    1.28
     refining
    1.22
     Refin
    1.20
     Refining
    1.19
     refined
    1.16
    Refinement
    1.15
     Refined
    1.14
    refined
    1.00
    Activations Density 0.004%

    No Known Activations