© 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. 19
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating sentences and emotional expressions

    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
    RenderAtEndOf
    -0.98
    uxxxx
    -0.96
     autorytatywna
    -0.96
     noDo
    -0.92
     Administrativna
    -0.92
     Taktlose
    -0.91
    NameInMap
    -0.88
    GOTREF
    -0.87
     ExecuteAsync
    -0.87
     zwiſchen
    -0.86
    POSITIVE LOGITS
    The
    0.53
     It
    0.52
     However
    0.50
     The
    0.48
     If
    0.48
    .
    0.47
     This
    0.46
     I
    0.45
    I
    0.45
     nôtre
    0.45
    Activations Density 3.591%

    No Known Activations