© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92620
    Prev
    Next
    INDEX
    Explanations

    delicious

    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
    AndEndTag
    -1.05
    aarrggbb
    -0.92
    Autoritní
    -0.90
    fjspx
    -0.85
    脚注の使い方
    -0.84
     EconPapers
    -0.82
     виправивши
    -0.82
    TestingModule
    -0.81
     AssemblyCulture
    -0.80
     initComponents
    -0.79
    POSITIVE LOGITS
    basicConfig
    0.46
     takes
    0.44
    umann
    0.43
     agradecimiento
    0.39
     empowers
    0.38
    文
    0.38
     condividere
    0.37
    他在
    0.36
    оз
    0.36
     reflects
    0.35
    Activations Density 0.000%

    No Known Activations