© 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. 2-RES-MATRYOSHKA-DC
    7. 2936
    Prev
    Next
    INDEX
    Explanations

    occurrences of the substring "ar" within words or text

    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
    Jeografia
    -0.81
    BagLayout
    -0.77
    contentValues
    -0.70
     estekak
    -0.70
     "..\..\..\
    -0.67
    InjectAttribute
    -0.66
    ècie
    -0.64
    первых
    -0.62
    ьаж
    -0.61
    ův
    -0.60
    POSITIVE LOGITS
    ar
    2.88
    AR
    2.48
    ars
    2.27
    ARS
    1.75
     ar
    1.70
     AR
    1.64
    Ar
    1.60
     Ar
    1.53
    arar
    1.41
    arin
    1.38
    Activations Density 0.080%

    No Known Activations