© 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. 390
    Prev
    Next
    INDEX
    Explanations

    mathematical notations involving exponents and indexing

    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
    ximity
    -0.49
    Lar
    -0.47
    <h3>
    -0.45
    People
    -0.44
    ”;
    -0.43
    Michele
    -0.43
    中
    -0.43
     Zeller
    -0.42
    er
    -0.41
    "},
    -0.41
    POSITIVE LOGITS
    }}^
    0.84
    })^
    0.82
     "^
    0.81
    ))^
    0.81
    }^
    0.80
    )^
    0.78
    ]^
    0.78
    $^
    0.77
     ^
    0.76
     /^
    0.76
    Activations Density 0.994%

    No Known Activations