© 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. 11008
    Prev
    Next
    INDEX
    Explanations

    references to specific named individuals, especially "Kat" and "Anne," or mentions of their names

    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
     lawn
    -0.87
     Lawn
    -0.76
    anol
    -0.69
     lawns
    -0.68
    Lawn
    -0.65
    lawn
    -0.55
     getItemId
    -0.55
     Alford
    -0.54
    moss
    -0.54
    anic
    -0.52
    POSITIVE LOGITS
     infar
    0.86
     Anne
    0.84
    Anne
    0.82
     Pumping
    0.80
     pumping
    0.74
    kat
    0.73
    AndEndTag
    0.62
     anne
    0.62
    CloseOperation
    0.60
     Morde
    0.60
    Activations Density 0.005%

    No Known Activations