© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 8005
    Prev
    Next
    INDEX
    Explanations

    phrases related to design and the act of designing

    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
    Negative Logits
     = 
    -0.91
    ThroughAttribute
    -0.86
    WebVitals
    -0.86
    fycat
    -0.83
     snippetHide
    -0.80
     Holbrook
    -0.78
    GEBURTSDATUM
    -0.77
    BIOGRAPHY
    -0.77
    apha
    -0.76
     Halley
    -0.74
    POSITIVE LOGITS
     Design
    1.34
    Design
    1.32
     design
    1.25
     Designs
    1.24
    DESIGN
    1.16
    Designs
    1.15
     designs
    1.13
     Designers
    1.13
     DESIGN
    1.11
    design
    1.07
    Activations Density 0.045%

    No Known Activations