© 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. 94192
    Prev
    Next
    INDEX
    Explanations

    Code and file locations

    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
     ComVisible
    -0.70
    ulemon
    -0.55
     للمعارف
    -0.55
    Believe
    -0.52
    EditorBrowsable
    -0.52
    CPtr
    -0.51
     EconPapers
    -0.51
     cherchés
    -0.50
    ñera
    -0.50
    RegistryLite
    -0.49
    POSITIVE LOGITS
    AnchorStyles
    0.66
    XmlAccessType
    0.57
    Archives
    0.55
    archi
    0.53
     незавершена
    0.53
    μία
    0.52
    insula
    0.52
     Pulaski
    0.52
     Precambrian
    0.52
    setVerticalGroup
    0.52
    Activations Density 0.002%

    No Known Activations