© 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. 15810
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "first" in relation to historical events or publications

    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
     nakalista
    -1.00
    OGND
    -0.90
    IndentedString
    -0.90
    EndContext
    -0.86
     AssemblyCompany
    -0.84
    ьаж
    -0.83
    interopRequire
    -0.79
     defaultstate
    -0.79
     Signalez
    -0.78
    CloseOperation
    -0.78
    POSITIVE LOGITS
    出版年
    0.56
     semula
    0.49
    érêt
    0.48
    ovich
    0.48
     ulang
    0.48
     Dorn
    0.47
     oval
    0.45
     file
    0.44
     source
    0.44
     us
    0.44
    Activations Density 0.022%

    No Known Activations