Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74383
    Prev
    Next
    INDEX
    Explanations

    Science/technical document context

    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
    ForValue
    -0.71
     InputDecoration
    -0.69
    GEBURTSDATUM
    -0.69
    getMenuInflater
    -0.65
    WebElementEntity
    -0.64
     ujednoznacz
    -0.61
     חיצוניים
    -0.60
     joaat
    -0.60
     Wiktionnaire
    -0.59
     AssemblyTitle
    -0.58
    POSITIVE LOGITS
     Plan
    0.62
     de
    0.59
    Plan
    0.58
     plan
    0.57
    plan
    0.56
    ọa
    0.54
     Compton
    0.50
     position
    0.50
     De
    0.49
     Plank
    0.48
    Activations Density 0.000%

    No Known Activations