© 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. 280
    Prev
    Next
    INDEX
    Explanations

    positive descriptions of experiences or feelings

    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
    Negative Logits
     tanggung
    -0.40
     different
    -0.39
     something
    -0.39
     utafitiHapana
    -0.39
     what
    -0.38
     radically
    -0.37
     which
    -0.36
    ESIS
    -0.36
     some
    -0.35
     potentially
    -0.35
    POSITIVE LOGITS
    excellent
    0.88
    good
    0.84
     GOOD
    0.81
    GOOD
    0.80
    tagHelperRunner
    0.77
    évaluateur
    0.76
    IUrlHelper
    0.76
    Excellent
    0.76
    Good
    0.75
     Excellent
    0.75
    Activations Density 5.788%

    No Known Activations