© 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. 30831
    Prev
    Next
    INDEX
    Explanations

    references to major television networks

    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
    Искәрмәләр
    -0.72
     mxArray
    -0.70
     OnDestroy
    -0.69
    ",$
    -0.65
     collo
    -0.64
    quec
    -0.62
     Cris
    -0.61
    /**
    -0.60
     Zhen
    -0.59
    Daw
    -0.59
    POSITIVE LOGITS
     ABC
    1.35
    ABC
    1.23
     abc
    0.99
    abc
    0.96
    Abc
    0.91
     Hoyt
    0.83
     Oppen
    0.82
     CBS
    0.80
    ----</
    0.80
     chapelle
    0.78
    Activations Density 0.010%

    No Known Activations