© 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. 0-CLT-HP
    7. 90617
    Prev
    Next
    INDEX
    Explanations

    communication

    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
     hand
    -0.92
    Hand
    -0.64
     hånd
    -0.63
    hand
    -0.58
     Hand
    -0.55
     animasi
    -0.47
    <bos>
    -0.47
     tangan
    -0.47
    zucht
    -0.46
     hands
    -0.45
    POSITIVE LOGITS
    GEBURTSDATUM
    1.00
    GOTREF
    0.91
    IntoConstraints
    0.82
    WaitGroup
    0.82
    ParallelGroup
    0.79
    awtextra
    0.79
     препратки
    0.79
    ConstraintMaker
    0.79
    SequentialGroup
    0.78
    </thead>
    0.77
    Activations Density 1.384%

    No Known Activations