© 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. 94739
    Prev
    Next
    INDEX
    Explanations

    Technical documents

    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
    MemoryWarning
    -0.64
     Exactos
    -0.60
     Issus
    -0.56
     Bering
    -0.55
    glie
    -0.55
    EReference
    -0.52
     Suez
    -0.50
     Chomsky
    -0.50
     philo
    -0.50
    richTextPanel
    -0.49
    POSITIVE LOGITS
    ac
    0.59
    */;
    0.55
     */;
    0.53
    acum
    0.52
     voks
    0.49
    acen
    0.48
    less
    0.47
     otomatig
    0.47
    ace
    0.47
    ecap
    0.46
    Activations Density 0.013%

    No Known Activations