Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 30981
    Prev
    Next
    INDEX
    Explanations

    the character sequence "sz"

    oai_token-act-pair · gemini-2.0-flash
    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
    invokeLater
    -1.07
     /\.
    -0.96
     sabbia
    -0.94
    IContainer
    -0.94
    pausal
    -0.85
    ++)
    
    -0.84
    createServer
    -0.84
     comigo
    -0.82
    routeProvider
    -0.82
    ])
    
    -0.81
    POSITIVE LOGITS
     Sz
    1.66
    Sz
    1.59
     sz
    1.54
    sz
    1.45
     SZ
    0.94
    SZ
    0.93
     Szcz
    0.88
    ysz
    0.75
     š
    0.71
     Ai
    0.70
    Activations Density 0.009%

    No Known Activations