© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4841
    Prev
    Next
    INDEX
    Explanations

    references to specific named individuals, particularly variations of the name "Kiki" or similar sounding names

    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
    躇
    -0.60
    IsMutable
    -0.59
    yelitis
    -0.58
     Kog
    -0.57
     Italij
    -0.56
     مشين
    -0.56
    Enllaces
    -0.56
    Sheldon
    -0.53
     Searle
    -0.53
     facie
    -0.52
    POSITIVE LOGITS
    ki
    3.41
    KI
    2.38
    Ki
    2.16
     ki
    2.08
     Ki
    2.03
     KI
    1.49
    iki
    1.45
    kiy
    1.40
    kii
    1.38
    kia
    1.30
    Activations Density 0.010%

    No Known Activations