© 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. 5-CLT-HP
    7. 93005
    Prev
    Next
    INDEX
    Explanations

    oversee

    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
    __(/*!
    -1.13
     '\\;'
    -0.90
    WriteTagHelper
    -0.88
    TemporalType
    -0.83
    mybatisplus
    -0.83
    adaptiveStyles
    -0.83
    jsxFileName
    -0.82
     صوتيه
    -0.82
     linkovi
    -0.82
     BrowserModule
    -0.80
    POSITIVE LOGITS
     completion
    0.54
     construction
    0.53
     building
    0.48
     installation
    0.43
     proper
    0.43
     laying
    0.42
     loading
    0.42
     final
    0.42
     work
    0.40
     ens
    0.40
    Activations Density 0.002%

    No Known Activations