© 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. 3244
    Prev
    Next
    INDEX
    Explanations

    inhale

    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
     B
    -0.37
    Composition
    -0.36
     composition
    -0.34
    化
    -0.34
     cientí
    -0.33
    անդ
    -0.33
     COMPOSITION
    -0.31
    B
    -0.30
    <bos>
    -0.30
    TableViewCell
    -0.30
    POSITIVE LOGITS
     незавершена
    0.81
     RIPRODUZIONE
    0.81
    Filmographie
    0.80
    Personensuche
    0.78
     raping
    0.75
    VideoCapture
    0.73
    fromnode
    0.73
    ])));
    0.73
    :✨
    0.70
    -------
    0.69
    Activations Density 0.001%

    No Known Activations