© 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. 45781
    Prev
    Next
    INDEX
    Explanations

    residency and 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
    DockStyle
    -1.14
     مشين
    -1.08
    IUrlHelper
    -1.04
    UnusedPrivate
    -1.02
    EndGlobalSection
    -0.99
    RenderAtEndOf
    -0.96
    EDEFAULT
    -0.96
     pinulongan
    -0.94
     defaultstate
    -0.93
    Personensuche
    -0.93
    POSITIVE LOGITS
     of
    0.65
     who
    0.51
     in
    0.42
     diberi
    0.40
    氓
    0.36
     whom
    0.35
     have
    0.35
     cent
    0.34
    who
    0.34
    ümer
    0.34
    Activations Density 0.036%

    No Known Activations