© 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. 4-CLT-HP
    7. 4484
    Prev
    Next
    INDEX
    Explanations

    names/code fragments

    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
     BYU
    -0.75
    SpringRunner
    -0.58
    DoubleQuotes
    -0.57
    BufferException
    -0.57
    TestingModule
    -0.55
    tség
    -0.54
     Utf
    -0.54
    >{@
    -0.54
    Carriera
    -0.53
    ppur
    -0.53
    POSITIVE LOGITS
    viewDidLoad
    0.50
    voorbeeld
    0.49
    Morphology
    0.48
    таратура
    0.48
    tro
    0.48
    SQLiteDatabase
    0.47
     Federal
    0.47
     architet
    0.47
    openapi
    0.47
    мино
    0.47
    Activations Density 0.000%

    No Known Activations