© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91764
    Prev
    Next
    INDEX
    Explanations

    biology/medicine/science

    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
    Not in Any Lists

    No Comments

    Negative Logits
     is
    -0.64
     was
    -0.63
     isn
    -0.55
    was
    -0.53
     wasn
    -0.51
    vignon
    -0.50
     reflects
    -0.49
     engages
    -0.49
    wasn
    -0.48
     transfieras
    -0.47
    POSITIVE LOGITS
    #+#
    0.73
     مرئيه
    0.61
    первых
    0.60
    lardır
    0.59
     that
    0.57
    estacks
    0.55
    AsUp
    0.54
     amelyek
    0.54
    ergies
    0.54
    Vidite
    0.52
    Activations Density 0.006%

    No Known Activations