© 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. 0-RES-MATRYOSHKA-DC
    7. 15634
    Prev
    Next
    INDEX
    Explanations

    references to oneself or expressions of personal involvement

    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
     he
    -1.04
     He
    -0.86
     a
    -0.83
     an
    -0.81
     it
    -0.79
     she
    -0.76
     in
    -0.75
     the
    -0.74
    ,
    -0.73
     his
    -0.72
    POSITIVE LOGITS
    AddAttribute
    2.05
     Monfieur
    1.27
     myſelf
    1.23
     Theſe
    1.21
     Efq
    1.14
     ſeveral
    1.07
     Anſ
    1.06
     ſmall
    1.06
     pleaſure
    1.04
     conmigo
    1.00
    Activations Density 0.402%

    No Known Activations