© 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. 1-CLT-HP
    7. 9523
    Prev
    Next
    INDEX
    Explanations

    cancer

    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
     [](
    -0.52
     chão
    -0.52
     })}
    -0.51
     qued
    -0.50
     $_[
    -0.50
     gerekiyor
    -0.49
    twin
    -0.48
    ++);
    -0.47
     }}>
    -0.47
     hoeft
    -0.47
    POSITIVE LOGITS
    AndEndTag
    0.63
     digestion
    0.57
     atrophy
    0.56
     typelib
    0.56
    reportWebVitals
    0.55
    тьяна
    0.55
    Datuak
    0.54
    setAccessible
    0.53
    styleType
    0.52
    драт
    0.52
    Activations Density 0.043%

    No Known Activations