© 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. 4925
    Prev
    Next
    INDEX
    Explanations

    tokens related to quotation marks and apostrophes

    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
    ,
    -0.51
     to
    -0.49
     (
    -0.47
     a
    -0.47
    ↵
    -0.45
    setVerticalGroup
    -0.44
     
    -0.44
     {
    -0.42
    anum
    -0.41
     for
    -0.41
    POSITIVE LOGITS
     $_"
    0.98
     Theſe
    0.92
     للمعارف
    0.91
     Diſ
    0.89
     onOptions
    0.86
    enumii
    0.85
     Monfieur
    0.84
    TargetException
    0.84
     Efq
    0.84
     Jefus
    0.83
    Activations Density 0.734%

    No Known Activations