© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 11733
    Prev
    Next
    INDEX
    Explanations

    references to specific identifiable entities or coded information, often represented by the token "PPP" with high activation

    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
    +:+
    -0.59
    jugend
    -0.54
     AO
    -0.54
    outSlope
    -0.54
     autorytatywna
    -0.54
     Diputados
    -0.54
     Вікі
    -0.53
     ANGELES
    -0.52
    tij
    -0.51
    chre
    -0.50
    POSITIVE LOGITS
    PPP
    2.70
     PPP
    2.52
     ppp
    1.76
    PPE
    1.69
     PPE
    1.54
    ppp
    1.26
    PPI
    0.78
     PPI
    0.68
    Geplaatst
    0.64
     disponibilités
    0.59
    Activations Density 0.001%

    No Known Activations