© 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. 76259
    Prev
    Next
    INDEX
    Explanations

    Technical, specific topics

    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
    FormTagHelper
    -0.56
     Ouverture
    -0.50
     nakalista
    -0.50
    LabelTagHelper
    -0.49
    ="@+
    -0.49
    )|^{
    -0.49
    XmlEnum
    -0.48
    XmlAccessorType
    -0.47
    Gön
    -0.47
     wishing
    -0.47
    POSITIVE LOGITS
    ifoli
    0.65
     practiced
    0.57
    GLFW
    0.55
    onMouse
    0.55
    devamını
    0.54
    LocationManager
    0.53
     gespielt
    0.52
    Personensuche
    0.52
     exercised
    0.52
    urance
    0.52
    Activations Density 0.000%

    No Known Activations