© 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. 10920
    Prev
    Next
    INDEX
    Explanations

    references to the word "arp," which is associated with the concept of deference or respect

    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
    GEBURTSDATUM
    -0.57
     Bac
    -0.55
    [++
    -0.54
    rizona
    -0.52
     Wikimedijinoj
    -0.50
     "..\..\..\
    -0.50
    DrawLine
    -0.49
    /*
    -0.48
    ElementException
    -0.48
     Santé
    -0.48
    POSITIVE LOGITS
    olid
    0.81
    instein
    0.80
    bst
    0.80
    iostream
    0.78
    laut
    0.75
    arp
    0.74
    Lw
    0.70
    VOA
    0.68
    vartis
    0.66
    υνα
    0.62
    Activations Density 0.042%

    No Known Activations