© 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. 1-CLT-HP
    7. 12225
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    FieldBuilder
    -0.69
    getRuntime
    -0.63
     تضيفلها
    -0.60
     AssemblyCompany
    -0.56
     <>",
    -0.56
    TestingModule
    -0.55
    MethodManager
    -0.55
    betical
    -0.52
     agrí
    -0.50
     uintptr
    -0.50
    POSITIVE LOGITS
     Gilmour
    0.59
     въ
    0.53
     cortas
    0.52
    EmptyString
    0.51
    ytä
    0.51
    metri
    0.51
     Baseline
    0.51
     corredores
    0.50
    cij
    0.50
    PHP
    0.50
    Activations Density 0.064%

    No Known Activations