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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-RES-MATRYOSHKA-DC
    7. 29394
    Prev
    Next
    INDEX
    Explanations

    the word "of" followed by definite articles or pronouns

    oai_token-act-pair · gemini-2.0-flash
    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
    '])){
    -0.68
     DialogInterface
    -0.61
     MIGHT
    -0.60
    edig
    -0.56
    ={
    -0.53
    : 
    -0.52
    ICING
    -0.51
     Mist
    -0.50
    gesetzt
    -0.50
    ']==
    -0.50
    POSITIVE LOGITS
    orteur
    0.94
     poffible
    0.93
    addPreferredGap
    0.83
     myſelf
    0.83
     itſelf
    0.82
     auffi
    0.82
     فريبيس
    0.81
    AndEndTag
    0.81
     ſche
    0.79
    ClientSize
    0.78
    Activations Density 0.026%

    No Known Activations