© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 987
    Prev
    Next
    INDEX
    Explanations

    references to old or aging entities

    oai_token-act-pair · gpt-4.1-nano
    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
     prior
    -0.68
     anteced
    -0.65
     previously
    -0.63
     دریافت‌شده
    -0.63
    OGND
    -0.61
     preced
    -0.60
     sebelumnya
    -0.60
    lardır
    -0.58
     wcześniej
    -0.58
     समीक्षाएं
    -0.58
    POSITIVE LOGITS
     old
    4.41
    old
    4.06
    Old
    3.92
     Old
    3.88
     OLD
    3.59
    OLD
    3.45
     vieux
    2.86
     viejo
    2.84
     oude
    2.63
     vieille
    2.59
    Activations Density 0.644%

    No Known Activations