© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92070
    Prev
    Next
    INDEX
    Explanations

    navigation and information traversal

    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
    GraphicsUnit
    -0.82
     يتيمه
    -0.76
     समीक्षक
    -0.63
    ‍♀️
    -0.62
    딪
    -0.60
    cookieParser
    -0.60
    middels
    -0.59
    latego
    -0.59
     UnityEditor
    -0.59
    ήσει
    -0.58
    POSITIVE LOGITS
     defaultstate
    0.56
    IndentedString
    0.48
    ViewImports
    0.47
    ➟
    0.47
    sho
    0.44
    tiftung
    0.44
     «
    0.42
    Diwedd
    0.42
    hamcrest
    0.41
    떨
    0.41
    Activations Density 0.177%

    No Known Activations