© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-RES-MATRYOSHKA-DC
    7. 29891
    Prev
    Next
    INDEX
    Explanations

    words and phrases that suggest someone is behaving foolishly or not facing facts

    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
    WEBPACK
    -0.56
     pymongo
    -0.51
    Bronnen
    -0.50
     Rog
    -0.49
     betrug
    -0.48
    phthal
    -0.46
     %>%
    -0.46
    ftig
    -0.46
    štu
    -0.46
    HasMaxLength
    -0.45
    POSITIVE LOGITS
     realism
    0.85
     realist
    0.81
     Realistic
    0.78
     realistic
    0.77
     réaliste
    0.77
    Reality
    0.76
    reality
    0.76
    Realistic
    0.75
     reality
    0.75
     realities
    0.73
    Activations Density 0.106%

    No Known Activations