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. 12-RES-MATRYOSHKA-DC
    4. 22436
    Prev
    Next
    INDEX
    Explanations

    mentions of taxpayers and investors

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ••••
    -0.78
     akong
    -0.68
     فريبيس
    -0.66
     Choisissez
    -0.65
    __*/
    -0.64
     commandant
    -0.64
    Географиясе
    -0.63
     المعرف
    -0.62
     Corsica
    -0.60
    SourceChecksum
    -0.60
    POSITIVE LOGITS
     Investors
    0.97
     investors
    0.94
    Investors
    0.91
     taxpayers
    0.88
    payers
    0.85
     Investor
    0.84
     shareholders
    0.77
     investor
    0.76
    PSK
    0.75
     taxpayer
    0.75
    Activations Density 0.006%

    No Known Activations