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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 9-RES-MATRYOSHKA-DC
    4. 16501
    Prev
    Next
    INDEX
    Explanations

    discussions of sustainability, human rights, and ethical consumerism

    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
     Efq
    -1.16
     becauſe
    -1.09
     myſelf
    -1.05
     Theſe
    -1.03
     Shakspeare
    -1.02
     uſed
    -0.98
     againſt
    -0.96
     themſelves
    -0.96
    Autoritní
    -0.94
     للمعارف
    -0.92
    POSITIVE LOGITS
     O
    0.56
     o
    0.52
    ,
    0.50
     end
    0.49
     
    0.48
     -
    0.48
     a
    0.47
     la
    0.47
    ?
    0.47
     (
    0.47
    Activations Density 0.041%

    No Known Activations