© 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. 32358
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a decline in a person's performance or abilities over time

    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
     historically
    -0.52
     noses
    -0.45
    ]").
    -0.44
     urma
    -0.44
    qPCR
    -0.43
     rispet
    -0.43
     betale
    -0.43
    ṃ
    -0.43
     today
    -0.43
     storici
    -0.43
    POSITIVE LOGITS
    ContentAsync
    0.72
    tvguidetime
    0.66
     nawr
    0.65
     فريبيس
    0.65
    makeText
    0.64
    Personensuche
    0.63
    Diwedd
    0.63
    ocell
    0.62
    出版年
    0.61
     nahilalakip
    0.61
    Activations Density 0.127%

    No Known Activations