© 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. 109
    Prev
    Next
    INDEX
    Explanations

    explicit references to processes or mechanisms in a systematic or analytical context

    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
     avoient
    -0.45
     rempliss
    -0.45
     étoient
    -0.43
     this
    -0.42
     pérdidas
    -0.42
     hjelp
    -0.41
     hjælp
    -0.40
     cuad
    -0.40
     pinulongan
    -0.39
     plads
    -0.39
    POSITIVE LOGITS
    tively
    0.70
    marily
    0.70
    sively
    0.69
    UTELY
    0.69
    mately
    0.69
    xically
    0.69
    ently
    0.68
    aneously
    0.68
    vily
    0.67
    ally
    0.66
    Activations Density 3.831%

    No Known Activations