© 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. 92479
    Prev
    Next
    INDEX
    Explanations

    technical/medical 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
    :✨
    -0.69
    XmlAccessorType
    -0.66
     estimés
    -0.61
    tagHelper
    -0.58
    richTextPanel
    -0.55
     سكانية
    -0.54
     tartalomajánló
    -0.54
     Affirmative
    -0.52
    riwal
    -0.52
    +#+
    -0.52
    POSITIVE LOGITS
    gy
    0.64
    getic
    0.55
    gonic
    0.52
    go
    0.49
    AxisAlignment
    0.48
    gon
    0.47
    MLLoader
    0.47
    protoimpl
    0.47
     Goya
    0.46
    gies
    0.46
    Activations Density 0.004%

    No Known Activations