© 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. 2647
    Prev
    Next
    INDEX
    Explanations

    Saving/Preservation

    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
    .
    -0.49
     by
    -0.45
     with
    -0.42
    :
    -0.42
     águas
    -0.41
    type
    -0.40
     natureza
    -0.39
     in
    -0.38
    nature
    -0.38
    lang
    -0.38
    POSITIVE LOGITS
     EconPapers
    0.90
    contentLoaded
    0.83
     ſtand
    0.79
     Monfieur
    0.76
    yntaxException
    0.74
     Majefty
    0.74
    SceneManagement
    0.73
    RegistryLite
    0.73
     Reſ
    0.73
     ſche
    0.73
    Activations Density 0.006%

    No Known Activations