© 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. 2159
    Prev
    Next
    INDEX
    Explanations

    of

    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
    umumkan
    -0.68
     quelcon
    -0.61
     soins
    -0.60
    Initializable
    -0.58
     différences
    -0.57
     leçons
    -0.56
     découver
    -0.56
     réguli
    -0.55
     économies
    -0.55
    WaitGroup
    -0.54
    POSITIVE LOGITS
     being
    0.68
     the
    0.58
    itology
    0.56
    ystema
    0.55
     it
    0.53
    antiation
    0.52
    keyColumn
    0.52
    pation
    0.51
    ELIA
    0.51
     impacting
    0.50
    Activations Density 0.005%

    No Known Activations