© 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. 1-CLT-HP
    7. 15507
    Prev
    Next
    INDEX
    Explanations

    oxane

    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
    OGND
    -0.84
    cheron
    -0.73
    enumi
    -0.68
     bezeichneter
    -0.67
    oules
    -0.67
    enumii
    -0.65
    iai
    -0.65
     تضيفلها
    -0.64
    grà
    -0.63
    UserScript
    -0.61
    POSITIVE LOGITS
    rafa
    0.52
    RegistryLite
    0.50
    ValueGenerated
    0.45
    principalTable
    0.44
    seck
    0.44
    stateProvider
    0.43
    styleType
    0.43
    ctividad
    0.41
     martie
    0.41
     rendel
    0.40
    Activations Density 0.223%

    No Known Activations