© 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. 2-RES-MATRYOSHKA-DC
    7. 2743
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "quoting."

    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
     Numerade
    -0.60
    netbeans
    -0.60
     wikipagina
    -0.59
     betweenstory
    -0.59
     ostavi
    -0.59
    fjspx
    -0.58
     AttributeError
    -0.57
    QA
    -0.56
     '{@
    -0.55
     Efq
    -0.55
    POSITIVE LOGITS
    oting
    2.47
    OTING
    0.97
    oted
    0.91
    Quoting
    0.73
    XmlAccessType
    0.66
    ote
    0.63
     quoting
    0.59
    OTER
    0.59
    oter
    0.57
    oters
    0.57
    Activations Density 0.004%

    No Known Activations