© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14108
    Prev
    Next
    INDEX
    Explanations

    references to individuals who are members of the same team or have a close personal connection

    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
    Traducción
    -0.61
    vanni
    -0.53
    Personendaten
    -0.53
    شوف
    -0.53
    ongiorno
    -0.52
    appeal
    -0.52
    versy
    -0.51
    sighs
    -0.51
    Aha
    -0.50
    Rujuakan
    -0.50
    POSITIVE LOGITS
     teammate
    3.05
     teammates
    2.89
     classmate
    1.53
     classmates
    1.45
     roommate
    1.39
    mmate
    1.25
    队友
    1.11
     roommates
    1.11
     countrymen
    0.81
     compagni
    0.79
    Activations Density 0.002%

    No Known Activations