© 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. 2-RES-MATRYOSHKA-DC
    7. 7158
    Prev
    Next
    INDEX
    Explanations

    references to Facebook and its associated messaging services

    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
    android
    -0.66
    mineral
    -0.60
    therly
    -0.59
    Unmarshaller
    -0.57
     Retrieval
    -0.57
    Parameteri
    -0.56
    ]='\
    -0.56
    Anar
    -0.56
    layah
    -0.55
     mineral
    -0.55
    POSITIVE LOGITS
     Facebook
    2.78
    Facebook
    2.56
     facebook
    2.38
    facebook
    2.25
     FACEBOOK
    2.25
    FACEBOOK
    2.08
     FB
    2.00
     Fb
    1.91
     fb
    1.84
    fb
    1.54
    Activations Density 0.021%

    No Known Activations