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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 40781
    Prev
    Next
    INDEX
    Explanations

    inspection and monitoring

    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
     monitoring
    -1.30
     Monitoring
    -1.23
    monitoring
    -1.20
    Monitoring
    -1.14
     inspection
    -1.09
     observation
    -1.09
     Inspection
    -1.02
     MONITORING
    -1.02
     Observation
    -1.00
    observation
    -0.99
    POSITIVE LOGITS
     of
    0.73
     list
    0.51
     disk
    0.51
    oa̍t
    0.50
     the
    0.48
    مو
    0.47
    fjspx
    0.47
     by
    0.47
     and
    0.47
    webElement
    0.46
    Activations Density 0.040%

    No Known Activations