© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2068
    Prev
    Next
    INDEX
    Explanations

    online text excerpts

    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
    bootstrapcdn
    -0.77
    onAttach
    -0.74
    webElementXpaths
    -0.73
     smtplib
    -0.73
    djangoproject
    -0.71
     lenker
    -0.70
    WithIOException
    -0.67
     defaultstate
    -0.67
    mybatisplus
    -0.66
     wireType
    -0.66
    POSITIVE LOGITS
     They
    0.65
     We
    0.64
     This
    0.56
     All
    0.53
     Our
    0.53
     You
    0.52
     Everyone
    0.52
     Everybody
    0.50
     tartalomajánló
    0.47
     There
    0.46
    Activations Density 0.006%

    No Known Activations