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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 2841
    Prev
    Next
    INDEX
    Explanations

    mentions of specific risk factors

    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
    новниш
    -0.91
     مرئيه
    -0.73
     мәкал
    -0.69
    ParallelGroup
    -0.67
    الحياه
    -0.65
     تانيه
    -0.62
    WebElementEntity
    -0.62
     препратки
    -0.61
    ціє
    -0.60
    
    -0.59
    POSITIVE LOGITS
     GenerationType
    0.69
     BorderRadius
    0.68
    GEBURTS
    0.64
    Lähteet
    0.53
    substack
    0.53
    WithMany
    0.51
    المناصب
    0.48
    RegisterType
    0.47
     stessi
    0.46
    SharedCtor
    0.46
    Activations Density 0.039%

    No Known Activations