© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 21257
    Prev
    Next
    INDEX
    Explanations

    references to loyalty and faithful relationships

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    InputBorder
    -0.65
    asticity
    -0.62
    ValueStyle
    -0.57
     arro
    -0.57
    Grig
    -0.55
    lang
    -0.55
     InputDecoration
    -0.54
     AppBundle
    -0.54
    Sucesor
    -0.54
    许
    -0.53
    POSITIVE LOGITS
     loyalty
    1.33
     Faithful
    1.30
    loyalty
    1.25
     loyal
    1.23
     faithfully
    1.19
     fidelity
    1.19
     loy
    1.18
     fidélité
    1.18
    Loy
    1.16
     faithfulness
    1.14
    Activations Density 0.010%

    No Known Activations