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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15180
    Prev
    Next
    INDEX
    Explanations

    expressions of strong negative judgment or insult

    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
    AddTagHelper
    -0.75
    SharedCtor
    -0.68
    ьаж
    -0.62
    зайн
    -0.57
    SuppressLint
    -0.56
    )}.
    -0.56
     Sequelize
    -0.56
     surely
    -0.55
    intios
    -0.55
    wix
    -0.55
    POSITIVE LOGITS
     idiot
    2.41
     asshole
    2.02
     jerk
    1.99
    idiot
    1.84
     moron
    1.75
     Idiot
    1.70
     idiots
    1.68
     jerks
    1.63
    Idiot
    1.63
     assholes
    1.55
    Activations Density 0.003%

    No Known Activations