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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90553
    Prev
    Next
    INDEX
    Explanations

    departed

    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
    tvguidetime
    -0.88
     CreateTagHelper
    -0.85
     سكانية
    -0.85
    ⓧ
    -0.84
    Personensuche
    -0.75
    IUrlHelper
    -0.75
     Exacts
    -0.73
     beginnetje
    -0.73
    tagHelperRunner
    -0.72
    LookAnd
    -0.71
    POSITIVE LOGITS
    s
    0.66
    esinde
    0.57
    ی
    0.57
    schaft
    0.56
    gracias
    0.55
     Atenas
    0.52
    a
    0.52
    ynthesis
    0.50
    vė
    0.48
    y
    0.48
    Activations Density 0.063%

    No Known Activations