© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 556
    Prev
    Next
    INDEX
    Explanations

    the word "old", and sometimes words associated with ancestry and history

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reaſon
    -0.80
     pleaſure
    -0.79
     myſelf
    -0.77
    lardır
    -0.77
     ſtate
    -0.75
     perſon
    -0.72
    脚注の使い方
    -0.70
     fubject
    -0.70
     raiſ
    -0.69
     Tiber
    -0.68
    POSITIVE LOGITS
     old
    3.22
     Old
    2.78
    Old
    2.77
    old
    2.69
     OLD
    2.66
    OLD
    2.28
     viejo
    2.13
     vieux
    2.08
     vecchio
    2.08
     vieja
    2.03
    Activations Density 0.127%

    No Known Activations