© 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. 11744
    Prev
    Next
    INDEX
    Explanations

    learn

    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
    learning
    -0.63
     Learning
    -0.60
    Learning
    -0.59
     learning
    -0.59
     comigo
    -0.55
     pluie
    -0.53
     aprendizaje
    -0.52
    WriteBarrier
    -0.52
     vastaan
    -0.51
     learns
    -0.51
    POSITIVE LOGITS
     about
    0.74
    ReactDOM
    0.61
    ########.
    0.61
     GenerationType
    0.59
     easy
    0.57
     [],
    0.56
    ContentAsync
    0.54
    SceneManagement
    0.54
    parsedMessage
    0.52
     the
    0.52
    Activations Density 0.016%

    No Known Activations