© 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. 97651
    Prev
    Next
    INDEX
    Explanations

    OSI

    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
     OSI
    -1.18
     للمعارف
    -0.92
    MemoryWarning
    -0.88
     متعلقه
    -0.87
    expandindo
    -0.84
    DoubleQuotes
    -0.82
     Brock
    -0.81
     CreateTagHelper
    -0.80
     disambiguazione
    -0.79
    KommentareTeilen
    -0.75
    POSITIVE LOGITS
     MRS
    0.48
    kaç
    0.44
    etr
    0.42
     Determin
    0.42
     LAT
    0.40
     LOB
    0.40
    إنه
    0.40
    oops
    0.39
    ness
    0.39
     DMC
    0.39
    Activations Density 0.083%

    No Known Activations