© 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. 1-CLT-HP
    7. 11813
    Prev
    Next
    INDEX
    Explanations

    "ove"

    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
    ove
    -2.64
    OVE
    -1.84
    oves
    -0.92
    ovem
    -0.80
    nove
    -0.66
    ovec
    -0.66
     ove
    -0.64
    AddTagHelper
    -0.59
    OV
    -0.58
    dove
    -0.57
    POSITIVE LOGITS
    UserScript
    0.59
    MLLoader
    0.57
     Roskov
    0.52
    ViewInit
    0.51
     entsch
    0.51
    hampton
    0.50
    halter
    0.50
    iers
    0.48
     Réponses
    0.48
    Jsp
    0.48
    Activations Density 0.014%

    No Known Activations