© 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. 0-CLT-HP
    7. 94036
    Prev
    Next
    INDEX
    Explanations

    medical/scientific texts

    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
     C
    -0.74
     F
    -0.59
    c
    -0.58
    f
    -0.56
     D
    -0.54
     c
    -0.54
    d
    -0.54
    le
    -0.52
    t
    -0.49
    l
    -0.48
    POSITIVE LOGITS
     مشين
    1.10
     للاسماء
    1.02
    tagHelperRunner
    0.99
    IntoConstraints
    0.96
    Personensuche
    0.94
    存于互联网档案馆
    0.92
    ImageContext
    0.91
     تضيفلها
    0.88
    脚注の使い方
    0.88
    WriteBarrier
    0.88
    Activations Density 0.155%

    No Known Activations