© 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
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14845
    Prev
    Next
    INDEX
    Explanations

    mentions of specific notable names and terms related to the "bona fide" concept

    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
     Fahr
    -0.52
     Elevator
    -0.50
     typelib
    -0.50
    Elevator
    -0.49
    Typo
    -0.49
    Fahr
    -0.48
    реди
    -0.46
     مخطط
    -0.46
    pecha
    -0.46
     contra
    -0.46
    POSITIVE LOGITS
     noun
    1.60
    Noun
    1.48
     Noun
    1.29
    noun
    1.24
     nouns
    1.22
     fide
    0.91
     senses
    0.79
     adjectives
    0.75
    rrggbb
    0.72
    Nou
    0.71
    Activations Density 0.004%

    No Known Activations