© 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-2-2B
    5. 1-CLT-HP
    7. 16177
    Prev
    Next
    INDEX
    Explanations

    approximately

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     financières
    -0.57
    <bos>
    -0.57
     perang
    -0.56
    hawar
    -0.56
    částí
    -0.54
     navegando
    -0.53
     poignée
    -0.51
    nestjs
    -0.51
     razie
    -0.50
     métallique
    -0.50
    POSITIVE LOGITS
     adenocarcinoma
    0.61
    aturing
    0.54
     lenti
    0.52
     ovaries
    0.51
     uterus
    0.50
     colic
    0.50
    rubin
    0.50
    coccus
    0.49
     facies
    0.49
     chol
    0.49
    Activations Density 0.013%

    No Known Activations