© 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-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 23
    Prev
    Next
    INDEX
    Explanations

    technical terminology and data related to scientific research or analysis

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    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
     
    -0.78
    ↵
    -0.55
    s
    -0.55
    The
    -0.54
     \
    -0.54
      
    -0.52
    \
    -0.52
    1
    -0.51
    A
    -0.50
    S
    -0.49
    POSITIVE LOGITS
     betweenstory
    1.58
    <unused14>
    1.40
    <unused28>
    1.40
    <unused41>
    1.40
    <unused79>
    1.40
    [@BOS@]
    1.39
    <unused3>
    1.39
    <unused8>
    1.39
    <unused16>
    1.39
    <unused23>
    1.39
    Activations Density 32.418%

    No Known Activations