© 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. 12214
    Prev
    Next
    INDEX
    Explanations

    on

    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
    SharedCtor
    -0.65
     '\\;'
    -0.62
     Италијани
    -0.62
    secutions
    -0.59
    Xna
    -0.56
     kasarigan
    -0.56
    yntaxException
    -0.56
    WithIOException
    -0.54
     nahilalakip
    -0.53
    SharedDtor
    -0.53
    POSITIVE LOGITS
     Saturday
    0.52
     Wednesday
    0.52
     Thursday
    0.50
     Sunday
    0.49
     Kamis
    0.49
     Friday
    0.49
     stage
    0.49
    -
    0.47
    Thursday
    0.47
     WEDNESDAY
    0.46
    Activations Density 0.022%

    No Known Activations