© 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. 5-CLT-HP
    7. 97031
    Prev
    Next
    INDEX
    Explanations

    Importance

    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
    webElementXpaths
    -0.59
    HideFlags
    -0.54
    CppMethod
    -0.53
    ViewImports
    -0.53
     оригіналу
    -0.52
    migrationBuilder
    -0.51
    vatar
    -0.51
     gesteld
    -0.47
    oprecipitation
    -0.47
    UNCIL
    -0.47
    POSITIVE LOGITS
     important
    0.86
     importance
    0.82
    importance
    0.81
     Important
    0.81
    Important
    0.81
    important
    0.80
    重要
    0.76
     importância
    0.74
     importante
    0.72
    Importance
    0.71
    Activations Density 0.011%

    No Known Activations