© 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. 302
    Prev
    Next
    INDEX
    Explanations

    revo

    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
    transQ
    -0.69
     Efq
    -0.68
     nakalista
    -0.65
     Wap
    -0.64
    __(/*!
    -0.63
    ArgsConstructor
    -0.61
    Aiheesta
    -0.60
    GEBURTSDATUM
    -0.57
     المعيارى
    -0.57
     thither
    -0.54
    POSITIVE LOGITS
     AssemblyCompany
    0.47
     forme
    0.46
    FormTagHelper
    0.45
     vícti
    0.45
    testcase
    0.44
     colesterol
    0.44
     résine
    0.44
    ogni
    0.43
    izzera
    0.43
    TING
    0.43
    Activations Density 0.011%

    No Known Activations