© 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. 24-RES-MATRYOSHKA-DC
    7. 1382
    Prev
    Next
    INDEX
    Explanations

    phrases that may express doubt in legal text

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     defaultstate
    -0.73
    Personendaten
    -0.62
    setVerticalGroup
    -0.60
    hésite
    -0.52
     Tatsache
    -0.50
    TagMode
    -0.49
     */
    -0.49
     knowledge
    -0.49
     esperienze
    -0.49
    HasForeignKey
    -0.49
    POSITIVE LOGITS
     significance
    1.08
     meaning
    0.99
     relevance
    0.98
     implications
    0.94
     impact
    0.90
     importance
    0.90
     Significance
    0.87
     value
    0.85
     ramifications
    0.83
     bearing
    0.82
    Activations Density 1.004%

    No Known Activations