© 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. 2-RES-MATRYOSHKA-DC
    7. 5282
    Prev
    Next
    INDEX
    Explanations

    references to the latter of two previously mentioned items or concepts

    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
     above
    -0.87
    above
    -0.82
    Above
    -0.75
     Above
    -0.75
     ABOVE
    -0.68
    enment
    -0.66
    Üdv
    -0.59
    below
    -0.59
     dieux
    -0.57
    zulegen
    -0.56
    POSITIVE LOGITS
     latter
    2.73
    后者
    1.91
    latter
    1.89
     Latter
    1.35
     letz
    1.22
     Послед
    0.96
     former
    0.90
     الأخيرة
    0.86
     both
    0.82
    both
    0.79
    Activations Density 0.015%

    No Known Activations