© 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. 0-CLT-HP
    7. 41463
    Prev
    Next
    INDEX
    Explanations

    technology

    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
    Personendaten
    -0.79
    InjectAttribute
    -0.69
     Baillargeon
    -0.69
     CreateTagHelper
    -0.66
    rowave
    -0.63
    WebVitals
    -0.63
    PerformLayout
    -0.63
     Normdatei
    -0.61
    AddTagHelper
    -0.61
    Rhestr
    -0.61
    POSITIVE LOGITS
    FileSize
    0.46
    LogError
    0.45
     mode
    0.45
    DebuggerNonUser
    0.44
     CGSize
    0.43
     sitting
    0.43
    void
    0.42
     album
    0.42
    Songs
    0.42
    liston
    0.42
    Activations Density 0.148%

    No Known Activations