© 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. 4-CLT-HP
    7. 2478
    Prev
    Next
    INDEX
    Explanations

    for

    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
    bootstrapcdn
    -0.94
     transfieras
    -0.70
     attempting
    -0.65
     trying
    -0.65
    IsContent
    -0.64
     cantando
    -0.58
     striving
    -0.56
    SourceChecksum
    -0.56
    Попис
    -0.56
     tentando
    -0.56
    POSITIVE LOGITS
    arrange
    0.55
     arrange
    0.52
     arranges
    0.50
     access
    0.48
    HomeAsUp
    0.48
    xions
    0.47
     arrangements
    0.46
    euvre
    0.45
    esine
    0.45
     Arrangements
    0.45
    Activations Density 0.001%

    No Known Activations