© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2969
    Prev
    Next
    INDEX
    Explanations

    articles

    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
    ern
    -0.45
    GRI
    -0.45
    Santis
    -0.44
     recev
    -0.44
    最快更新
    -0.44
    ($"{
    -0.43
    toMap
    -0.43
    GUILayout
    -0.42
     Rig
    -0.41
    fiées
    -0.41
    POSITIVE LOGITS
    tagext
    0.78
     CreateTagHelper
    0.71
     Arguments
    0.59
    kmale
    0.58
    douard
    0.57
     pram
    0.57
    gadier
    0.56
     EconPapers
    0.56
     resourceCulture
    0.55
    urcht
    0.54
    Activations Density 0.002%

    No Known Activations