© 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. 2881
    Prev
    Next
    INDEX
    Explanations

    post

    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
    virons
    -0.62
    änomen
    -0.61
    uteurs
    -0.61
    InitVars
    -0.60
    queryInterface
    -0.57
    riwal
    -0.57
    omores
    -0.56
    enumii
    -0.55
    auté
    -0.55
    OnAdd
    -0.54
    POSITIVE LOGITS
     of
    0.55
    IntoConstraints
    0.51
     magnético
    0.45
     cinematogra
    0.43
    routeProvider
    0.42
     techo
    0.41
     falls
    0.40
     maestra
    0.40
    stateProvider
    0.40
    Magnetic
    0.39
    Activations Density 0.001%

    No Known Activations