© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1198
    Prev
    Next
    INDEX
    Explanations

    Names and Places

    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
     Architect
    -0.77
    Architect
    -0.69
     getResources
    -0.55
    ministrazione
    -0.54
    poque
    -0.52
     AttributeSet
    -0.51
    ತ್ತು
    -0.50
     Captains
    -0.50
     TÉCN
    -0.50
    loren
    -0.50
    POSITIVE LOGITS
    ing
    0.77
     незавершена
    0.77
    UnitTesting
    0.68
    ages
    0.61
    بوابة
    0.57
     snippetHide
    0.56
    ingly
    0.55
    u
    0.55
     AssemblyTitle
    0.54
    RSpec
    0.52
    Activations Density 0.111%

    No Known Activations