© 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. 13804
    Prev
    Next
    INDEX
    Explanations

    sequences of characters representing specific laboratory or technical codes, particularly those involving the pattern "hk" or "HK" with surrounding alphanumeric characters

    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
    PerformLayout
    -0.55
    ArrowToggle
    -0.48
     Berthe
    -0.48
     bucket
    -0.47
    Bucket
    -0.47
     Pluto
    -0.46
     Plut
    -0.46
     Bucket
    -0.45
     Zon
    -0.45
    Földrajzportál
    -0.44
    POSITIVE LOGITS
    HK
    3.02
     HK
    2.28
    hk
    2.13
     hk
    1.44
    Hk
    1.21
    WriteLiteral
    0.84
     незавершена
    0.79
    ">//
    0.73
    
    0.73
    AnchorStyles
    0.71
    Activations Density 0.002%

    No Known Activations