© 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. 20-CLT-HP
    7. 72929
    Prev
    Next
    INDEX
    Explanations

    starting/beginning

    np_max-act-logits · 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
    DNEY
    -0.75
    runApp
    -0.61
    OGND
    -0.61
    ]));
    -0.59
     typedef
    -0.58
     '\\;'
    -0.58
    Poloha
    -0.56
    ,:);
    -0.56
    IRMED
    -0.56
    HtmlAttribute
    -0.55
    POSITIVE LOGITS
     starting
    0.94
    starting
    0.73
     Starting
    0.73
    Starting
    0.71
     initiating
    0.69
     initiation
    0.69
     beginning
    0.66
    invokeLater
    0.64
     initiated
    0.63
     initi
    0.62
    Activations Density 0.001%

    No Known Activations