© 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. 2603
    Prev
    Next
    INDEX
    Explanations

    s

    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
    Билгалдахарш
    -0.53
    addGap
    -0.47
    getMenuInflater
    -0.47
     world
    -0.45
    laştır
    -0.45
     nakalista
    -0.44
     reputation
    -0.44
    عيد
    -0.43
     makeStyles
    -0.43
     name
    -0.43
    POSITIVE LOGITS
     spokespersons
    0.65
     summits
    0.58
     neighbors
    0.57
     strangers
    0.57
    Amigos
    0.57
     actresses
    0.57
     scientists
    0.56
     prophets
    0.56
     celebrities
    0.56
    }];
    0.56
    Activations Density 0.012%

    No Known Activations