Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 865
    Prev
    Next
    INDEX
    Explanations

    of

    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
    AndEndTag
    -0.60
    NonQuery
    -0.54
     JSTOR
    -0.53
    enumi
    -0.52
    SpringRunner
    -0.52
    criminator
    -0.50
     VIVO
    -0.50
    riwal
    -0.49
    Configured
    -0.49
    cipline
    -0.48
    POSITIVE LOGITS
     maç
    0.57
     secretory
    0.54
    RectangleBorder
    0.54
    ollectionView
    0.52
    InputBorder
    0.52
     Automat
    0.52
    FXMLLoader
    0.52
    ölkerung
    0.51
     countdown
    0.51
     reusable
    0.51
    Activations Density 0.238%

    No Known Activations