© 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. 223
    Prev
    Next
    INDEX
    Explanations

    images and visual representations in scientific contexts

    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
    ########.
    -0.81
     &___
    -0.70
     Houſe
    -0.68
    <unused43>
    -0.67
    iſchen
    -0.67
    <unused23>
    -0.66
    <unused8>
    -0.66
    <unused74>
    -0.66
    <pad>
    -0.66
    <unused41>
    -0.66
    POSITIVE LOGITS
    </i>
    0.40
    </b>
    0.39
     close
    0.39
    Personendaten
    0.39
     AssemblyProduct
    0.38
    </em>
    0.36
    </u>
    0.35
    ↵
    0.34
     (
    0.34
    Filmografie
    0.34
    Activations Density 2.661%

    No Known Activations