© 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. 97582
    Prev
    Next
    INDEX
    Explanations

    mobility

    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
     Mobility
    -0.74
     mobility
    -0.65
    Mobility
    -0.61
    ou
    -0.60
     alimentaires
    -0.59
     mobilité
    -0.59
    issau
    -0.59
    DataMember
    -0.58
    mybatisplus
    -0.57
    toFixed
    -0.57
    POSITIVE LOGITS
    s
    0.57
    ly
    0.55
     виправивши
    0.52
    Скачать
    0.49
    ding
    0.47
    neath
    0.47
    nya
    0.47
     snippetHide
    0.46
    setVerticalGroup
    0.46
    rzez
    0.45
    Activations Density 0.059%

    No Known Activations