© 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. 5-CLT-HP
    7. 1205
    Prev
    Next
    INDEX
    Explanations

    programming 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
     masas
    -0.52
    hyrchwyd
    -0.50
     gradova
    -0.46
    GeneratedCode
    -0.46
    Bronnen
    -0.45
     volet
    -0.45
     AssemblyTitle
    -0.45
     cápsulas
    -0.45
    gencia
    -0.45
     chiunque
    -0.44
    POSITIVE LOGITS
    AndEndTag
    0.83
    SourceChecksum
    0.76
    SharedDtor
    0.65
    enumii
    0.65
    queryInterface
    0.63
     насељу
    0.61
    ConverterFactory
    0.61
    awtextra
    0.60
     विश्वसनीयता
    0.59
    évaluateur
    0.58
    Activations Density 0.017%

    No Known Activations