© 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. 6833
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to trust and 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
    Рабо
    -0.81
     Anaconda
    -0.79
    Appender
    -0.77
     ALC
    -0.77
    φέρ
    -0.77
     bere
    -0.75
     Notepad
    -0.75
    onedDateTime
    -0.75
     Specimens
    -0.74
     Capo
    -0.74
    POSITIVE LOGITS
     trust
    2.08
    Trust
    2.00
     Trust
    1.95
    trust
    1.94
    TRUST
    1.88
     TRUST
    1.85
     trusts
    1.81
     trusting
    1.69
     trusted
    1.61
     Trusts
    1.48
    Activations Density 0.060%

    No Known Activations