© 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. 15596
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly the word "friend."

    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
    Friends
    -1.32
     Friends
    -1.31
     FRIENDS
    -1.23
     friends
    -1.23
     partners
    -1.22
     buddies
    -1.20
    friends
    -1.14
     mates
    -1.13
     pals
    -1.12
     Partners
    -1.02
    POSITIVE LOGITS
     friend
    1.45
     colleague
    0.96
     Friend
    0.92
    NameInMap
    0.81
    VersionUID
    0.79
    Referencie
    0.79
    Datuak
    0.78
    friend
    0.77
     protoimpl
    0.74
    ThroughAttribute
    0.69
    Activations Density 0.003%

    No Known Activations