© 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. 0-CLT-HP
    7. 92015
    Prev
    Next
    INDEX
    Explanations

    locally

    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
     local
    -1.27
    local
    -1.02
     locally
    -0.98
     lokal
    -0.82
     lokale
    -0.82
     lokalen
    -0.78
    Local
    -0.75
     местных
    -0.72
     Local
    -0.69
     LOCAL
    -0.69
    POSITIVE LOGITS
    ⓧ
    0.90
     iſt
    0.85
     Clima
    0.85
     itſelf
    0.84
     ―――――
    0.83
     doubtnut
    0.81
     Monfieur
    0.81
    enumi
    0.78
     Efq
    0.77
    izations
    0.76
    Activations Density 0.063%

    No Known Activations