© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97809
    Prev
    Next
    INDEX
    Explanations

    gathering locations

    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
    ValueStyle
    -0.60
     varandra
    -0.56
     together
    -0.54
     réunions
    -0.52
     Grecs
    -0.52
     devoirs
    -0.51
     réunis
    -0.51
     reunión
    -0.51
     Gathering
    -0.49
     juntas
    -0.49
    POSITIVE LOGITS
     '\\;'
    0.72
    rawDesc
    0.63
     to
    0.60
    serviceWorker
    0.58
    sior
    0.58
    rungsseite
    0.56
    tagHelperRunner
    0.56
    awaiter
    0.56
    </>
    0.55
    rrggbb
    0.55
    Activations Density 0.006%

    No Known Activations