© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2809
    Prev
    Next
    INDEX
    Explanations

    computer memory

    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
    })));
    -0.46
     Anexo
    -0.42
    bide
    -0.41
    ZZI
    -0.40
    gemm
    -0.40
     boto
    -0.40
     Pa
    -0.40
    盤
    -0.39
     All
    -0.39
    visiae
    -0.39
    POSITIVE LOGITS
    InjectAttribute
    0.92
    хьтан
    0.85
     protoimpl
    0.77
    setVerticalGroup
    0.76
    awtextra
    0.75
     Signalez
    0.73
    Демографія
    0.72
     Roskov
    0.72
     חיצוניים
    0.70
     contextLoads
    0.70
    Activations Density 0.003%

    No Known Activations