© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97289
    Prev
    Next
    INDEX
    Explanations

    positive interactions/nourishment

    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
     feeding
    -1.02
    scheme
    -0.92
     Feeding
    -0.92
    Feeding
    -0.85
     nourrir
    -0.84
    feeding
    -0.79
     Scheme
    -0.76
     scheme
    -0.71
     nourishing
    -0.70
     nourished
    -0.69
    POSITIVE LOGITS
    ement
    0.65
    verwijspagina
    0.61
    PropertyChanging
    0.60
    homonymie
    0.59
    StructEnd
    0.57
     externi
    0.57
     BorderRadius
    0.56
     endblock
    0.56
    ings
    0.55
    Viitteet
    0.54
    Activations Density 1.292%

    No Known Activations