© 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. 904
    Prev
    Next
    INDEX
    Explanations

    2

    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
    ParallelGroup
    -0.67
     russes
    -0.58
     ecosystem
    -0.54
    ABBA
    -0.54
    wiel
    -0.54
     emperors
    -0.53
    Aman
    -0.53
     Aman
    -0.52
     grama
    -0.52
     ecosystems
    -0.52
    POSITIVE LOGITS
     '\\;'
    0.66
    s
    0.56
    Aiheesta
    0.56
    GenerationType
    0.51
     getItemId
    0.51
    adpleegd
    0.48
     Also
    0.47
    ILD
    0.46
    ंदीखरीदारी
    0.46
    InjectMocks
    0.45
    Activations Density 0.044%

    No Known Activations