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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10660
    Prev
    Next
    INDEX
    Explanations

    Moving toward something

    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
    DeleteBehavior
    -0.88
    parsedMessage
    -0.87
    ItemBackground
    -0.81
    RTGC
    -0.76
     utafitiHapana
    -0.76
    ControllerAdvice
    -0.75
    ArrowToggle
    -0.73
     ujednoznacz
    -0.72
     Italijani
    -0.72
     وتسجيلات
    -0.71
    POSITIVE LOGITS
    osten
    0.45
     a
    0.43
    룸
    0.40
    étend
    0.40
    sikker
    0.40
    ској
    0.40
    相同的
    0.38
     naranja
    0.37
    Enum
    0.37
    Default
    0.37
    Activations Density 0.022%

    No Known Activations