© 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. 1019
    Prev
    Next
    INDEX
    Explanations

    micro

    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
     micro
    -1.34
     Micro
    -1.23
    micro
    -1.23
    Micro
    -1.20
     MICRO
    -1.01
    MICRO
    -0.94
     Microb
    -0.90
     micros
    -0.89
     mikro
    -0.86
    マイクロ
    -0.84
    POSITIVE LOGITS
    GEBURTSDATUM
    0.52
    +#+#
    0.52
    fromnode
    0.50
    TemporalType
    0.50
     negocios
    0.47
    tadır
    0.46
    WebElementEntity
    0.45
    Barre
    0.43
    antaranya
    0.43
    aggi
    0.42
    Activations Density 0.114%

    No Known Activations