© 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. 3002
    Prev
    Next
    INDEX
    Explanations

    expressions of honesty and sincerity

    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
    ⓧ
    -0.66
    complexContent
    -0.65
    RegistryLite
    -0.60
    InjectAttribute
    -0.58
     Roskov
    -0.57
    
    -0.54
     Fabulous
    -0.54
     facto
    -0.53
    ệ
    -0.51
    出版年
    -0.51
    POSITIVE LOGITS
     honest
    2.59
    honest
    2.33
    Honest
    2.16
     Honest
    2.14
     honesty
    1.98
     genuine
    1.95
     honestly
    1.94
     genuinely
    1.83
     sincere
    1.76
    genuine
    1.70
    Activations Density 0.093%

    No Known Activations