© 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. 17204
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing challenges and complexities in situations

    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
     similarly
    -0.54
    ]--;
    -0.53
    phosa
    -0.52
     BrowserModule
    -0.49
    Искәрмәләр
    -0.46
    contentLoaded
    -0.46
    WriteTagHelper
    -0.45
     Similarly
    -0.45
    documentclass
    -0.45
    arakat
    -0.44
    POSITIVE LOGITS
     pleaſure
    0.70
     Theſe
    0.67
     Eſ
    0.66
    Whole
    0.65
     Swedes
    0.65
    Igles
    0.65
     defaultstate
    0.65
     ―――――
    0.65
     myſelf
    0.65
     OGS
    0.64
    Activations Density 0.054%

    No Known Activations