© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75980
    Prev
    Next
    INDEX
    Explanations

    Scientific/medical contexts

    np_max-act-logits · 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
    expandindo
    -0.88
     Waray
    -0.84
    MessageOf
    -0.83
    HomeAsUpEnabled
    -0.80
    contentLoaded
    -0.79
     فريبيس
    -0.76
     NSCoder
    -0.74
    сылкі
    -0.73
     jScrollPane
    -0.72
     ddelweddau
    -0.71
    POSITIVE LOGITS
    dle
    0.54
    le
    0.48
    cle
    0.43
    sel
    0.42
    let
    0.40
    uncle
    0.39
    tle
    0.37
    gle
    0.37
    tel
    0.36
     revés
    0.36
    Activations Density 0.002%

    No Known Activations