© 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. 13134
    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
    发表于
    -0.56
     plupart
    -0.50
     المعيارى
    -0.48
     BoxDecoration
    -0.48
    toli
    -0.46
     correctes
    -0.46
     annuelle
    -0.44
    tagHelper
    -0.44
     prochaines
    -0.44
     kväll
    -0.43
    POSITIVE LOGITS
    setVerticalGroup
    0.75
     attacks
    0.68
     when
    0.67
    MessageTagHelper
    0.63
     atrocities
    0.63
    <bos>
    0.60
     battles
    0.60
     events
    0.59
     Indians
    0.59
     earthquakes
    0.59
    Activations Density 0.033%

    No Known Activations