© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38973
    Prev
    Next
    INDEX
    Explanations

    models

    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
     models
    -1.97
     structures
    -1.59
     Models
    -1.57
    models
    -1.50
    Models
    -1.38
     MODELS
    -1.27
     Modelle
    -1.23
     designs
    -1.19
     modelos
    -1.18
     Structures
    -1.05
    POSITIVE LOGITS
     épaules
    0.66
     genoux
    0.63
    chedule
    0.58
    aving
    0.57
     jambes
    0.57
    ickness
    0.56
    новништво
    0.56
    urface
    0.55
    __);
    0.55
     battre
    0.54
    Activations Density 0.236%

    No Known Activations