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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13883
    Prev
    Next
    INDEX
    Explanations

    code or references related to web page elements such as titles, links, or metadata

    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
     houſe
    -0.90
     myſelf
    -0.85
     Titles
    -0.83
     Houſe
    -0.81
     ſmall
    -0.81
     titles
    -0.80
     Majefty
    -0.79
     pleaſure
    -0.79
     themſelves
    -0.77
     Efq
    -0.77
    POSITIVE LOGITS
    title
    1.38
    脚注の使い方
    0.58
    PRNewswire
    0.58
    はじめに
    0.55
    bibitem
    0.54
    __(/*!
    0.54
    utsche
    0.52
    UnitOfWork
    0.52
    MessageOf
    0.52
     Signalez
    0.51
    Activations Density 0.005%

    No Known Activations