© 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. 23678
    Prev
    Next
    INDEX
    Explanations

    phrases expressing opinions and thoughts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    adoc
    -0.54
     cherchez
    -0.54
     מלא
    -0.50
     emplois
    -0.49
    렵
    -0.49
     ordres
    -0.49
     codes
    -0.49
    Publishers
    -0.47
     calendriers
    -0.47
     pulito
    -0.47
    POSITIVE LOGITS
     opinions
    0.97
     Opinions
    0.94
    Opinions
    0.90
    Thoughts
    0.90
     opinion
    0.87
     Thoughts
    0.87
    opinions
    0.87
     opin
    0.77
    opinion
    0.75
     Opinion
    0.74
    Activations Density 0.104%

    No Known Activations