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. 74369
    Prev
    Next
    INDEX
    Explanations

    graduation degrees

    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
     abb
    -0.43
     sub
    -0.40
    Incon
    -0.36
     colle
    -0.36
    Barra
    -0.35
    さ
    -0.35
     mini
    -0.35
     sweets
    -0.34
    SPONSORED
    -0.34
    зион
    -0.34
    POSITIVE LOGITS
    RTEE
    0.71
     Athletic
    0.69
     transfieras
    0.68
    ActionCreators
    0.68
    Sklici
    0.66
    kine
    0.66
    WriteAttribute
    0.63
     Occupational
    0.63
     Exercise
    0.63
     Nutrition
    0.63
    Activations Density 0.001%

    No Known Activations