© 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. 4511
    Prev
    Next
    INDEX
    Explanations

    references to a proper noun in all capital letters

    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
    ambique
    -0.84
    complexType
    -0.72
     auffi
    -0.68
     Kyrgyz
    -0.68
    styleType
    -0.65
     république
    -0.65
     Tigre
    -0.64
     Segurança
    -0.64
    Coppa
    -0.64
     مرئيه
    -0.64
    POSITIVE LOGITS
     HAL
    3.25
     Hal
    3.00
    HAL
    2.89
    Hal
    2.88
     hal
    2.86
    hal
    2.69
     Halo
    2.28
     halo
    2.25
    Halo
    2.19
    halo
    2.13
    Activations Density 0.007%

    No Known Activations