© 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. 31461
    Prev
    Next
    INDEX
    Explanations

    references to time periods, specifically decades

    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
     Weir
    -0.66
    soo
    -0.63
     Wheatley
    -0.63
    ganggu
    -0.59
     מאוד
    -0.57
    Weir
    -0.57
    ngths
    -0.56
     alia
    -0.56
    siswa
    -0.56
     AssemblyCulture
    -0.56
    POSITIVE LOGITS
     ―――――
    1.36
     Decade
    1.27
     myſelf
    1.14
     ſtate
    1.10
     juſt
    1.10
     decade
    1.09
     leaſt
    1.09
     Majefty
    1.09
     purpoſe
    1.08
     ſind
    1.05
    Activations Density 0.005%

    No Known Activations