© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15850
    Prev
    Next
    INDEX
    Explanations

    references to the mythical bird "phoenix," symbolizing rebirth or renewal

    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
     المعيارى
    -0.81
     OFDb
    -0.79
     disambiguazione
    -0.74
    ьаж
    -0.73
     CreateTagHelper
    -0.73
    protoimpl
    -0.73
     AssemblyCulture
    -0.71
    EndGlobalSection
    -0.71
    mybatisplus
    -0.70
     esternos
    -0.70
    POSITIVE LOGITS
     Phoenix
    2.48
    Phoenix
    2.30
     phoenix
    2.02
    phoenix
    1.73
    ENIX
    1.15
     PHO
    1.10
    PHO
    0.88
    凤凰
    0.81
    agi
    0.68
    addCriterion
    0.66
    Activations Density 0.004%

    No Known Activations